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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105150
    Prev
    Next
    INDEX
    Explanations

    statistical or numerical data and measurements.

    oai_token-act-pair · gpt-4oTriggered by @joshengels

    punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     autorytatywna
    -0.96
    uxxxx
    -0.94
     Administrativna
    -0.92
     Taktlose
    -0.89
    RenderAtEndOf
    -0.88
     zwiſchen
    -0.88
    ロウィン
    -0.85
     geſch
    -0.83
    IntoConstraints
    -0.83
    NameInMap
    -0.83
    POSITIVE LOGITS
    The
    0.54
     duquel
    0.50
     If
    0.50
     It
    0.49
    .
    0.46
    If
    0.46
    No
    0.44
    I
    0.44
     However
    0.44
     This
    0.44
    Activations Density 2.363%

    No Known Activations