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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9074
    Prev
    Next
    INDEX
    Explanations

    mentions of notable public figures related to various events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.31
    <eos>
    -0.30
    ,
    -0.29
     and
    -0.28
    ...
    -0.27
    ic
    -0.23
    '
    -0.22
     Kaplan
    -0.22
    1
    -0.22
     we
    -0.22
    POSITIVE LOGITS
     مشين
    1.12
    [@BOS@]
    1.09
    <unused16>
    1.09
    <unused42>
    1.09
    <unused43>
    1.09
    <pad>
    1.09
    <unused3>
    1.09
    <unused41>
    1.09
    <unused51>
    1.09
    <unused28>
    1.09
    Activations Density 0.463%

    No Known Activations