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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11609
    Prev
    Next
    INDEX
    Explanations

    molecular and biological terminology related to developmental stages and genetic factors in organisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.51
     visually
    -0.47
     in
    -0.47
    ,
    -0.45
     come
    -0.43
    -
    -0.42
     \
    -0.42
     (
    -0.40
     on
    -0.39
     like
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.94
     beſti
    0.93
    <unused43>
    0.93
    <unused42>
    0.92
    <unused41>
    0.92
    <unused16>
    0.92
    <pad>
    0.92
    <unused51>
    0.92
    <unused28>
    0.92
    <unused23>
    0.92
    Activations Density 1.153%

    No Known Activations