© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1885
    Prev
    Next
    INDEX
    Explanations

    references to statistical models, parameters, and relationships in data

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

    citation references and bibliographic markers in academic and technical documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     $_"
    -0.49
    >--}}
    -0.35
    +|
    -0.35
    verifyException
    -0.35
    principalColumn
    -0.33
    &
    
    -0.33
    psin
    -0.33
    AxisAlignment
    -0.32
     '/')
    -0.32
    '</
    -0.32
    POSITIVE LOGITS
     surla
    0.65
    ViewFeatures
    0.61
    出版年
    0.57
     estekak
    0.55
    AndEndTag
    0.55
    httphttps
    0.55
    Demografie
    0.54
     المعيارى
    0.53
     الرياضيه
    0.50
    号線
    0.50
    Activations Density 2.155%

    No Known Activations