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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5627
    Prev
    Next
    INDEX
    Explanations

    characters and symbols used in programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maybe
    -0.46
     nevertheless
    -0.42
     hence
    -0.35
     nonetheless
    -0.35
     also
    -0.35
    -,
    -0.35
     hers
    -0.35
     either
    -0.35
     still
    -0.34
     how
    -0.33
    POSITIVE LOGITS
    parsedMessage
    0.77
    :✨
    0.74
    其
    0.73
    𑄮
    0.69
    <unused32>
    0.69
    <unused6>
    0.68
     メンテナ
    0.68
    <unused1>
    0.68
    <unused21>
    0.68
    <unused76>
    0.68
    Activations Density 0.007%

    No Known Activations