© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13396
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging techniques and associated findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific citations and reference numbers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    numeric citations in academic papers, particularly those in reference tags with formatting markers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    academic citation references and citations numbers in brackets.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    reference numbers in academic citations, especially in the range of 40-49.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references and citation markers in scientific text, especially bracketed reference numbers and figure/table identifiers.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.62
    ])):
    -0.62
    '}),
    -0.62
    migrationBuilder
    -0.61
    __':
    -0.60
    )"),
    -0.58
    ']):
    -0.57
    ')):
    -0.57
    featureID
    -0.57
    }}:
    -0.57
    POSITIVE LOGITS
    出版年
    0.66
    intéress
    0.54
     koron
    0.46
     című
    0.44
    ंदीखरीदारी
    0.44
     gustado
    0.42
    ándolos
    0.42
    homonymie
    0.42
    原始内容存档
    0.40
    reszcie
    0.40
    Activations Density 0.977%

    No Known Activations