Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120172
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or uncertainty

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

    isn't really

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Inscrivez
    -0.59
    ViewImports
    -0.52
     avoient
    -0.47
     pouvoit
    -0.47
    fromCharCode
    -0.43
     étoit
    -0.43
    GIVEREF
    -0.42
    PathVariable
    -0.42
     múltiple
    -0.42
     HasFactory
    -0.42
    POSITIVE LOGITS
    lında
    0.60
    really
    0.60
    Really
    0.59
     really
    0.57
    不太
    0.56
     layui
    0.55
     Really
    0.55
    pretty
    0.55
     Hardly
    0.52
     egentlig
    0.51
    Activations Density 0.016%

    No Known Activations