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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14547
    Prev
    Next
    INDEX
    Explanations

    phrases indicating caution or specific conditions related to health risks or variables

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

    adverbs indicating emphasis or specificity (like "particularly", "especially").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     altra
    -0.43
     sola
    -0.42
    getMenuInflater
    -0.38
    <()>
    -0.38
     another
    -0.38
    owiec
    -0.36
    LabelTagHelper
    -0.36
    enda
    -0.36
     setInterval
    -0.35
     CreateTagHelper
    -0.35
    POSITIVE LOGITS
     particularly
    0.82
     especially
    0.82
    Especially
    0.81
    particularly
    0.80
    especially
    0.77
     specialmente
    0.73
     szczególnie
    0.71
    特别是
    0.71
     Particularly
    0.69
     Especially
    0.69
    Activations Density 0.241%

    No Known Activations