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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 6176
    Prev
    Next
    INDEX
    Explanations

    references to observation and scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    at
    -1.32
     At
    -1.22
    At
    -1.20
    AT
    -1.16
     @
    -1.03
     AT
    -0.90
    @
    -0.90
     tại
    -0.85
     oleh
    -0.79
    ＠
    -0.78
    POSITIVE LOGITS
    ={({
    0.37
    haikusbot
    0.36
    WebpackPlugin
    0.35
    getWindow
    0.34
    QMetaType
    0.33
    Audiobook
    0.33
    wantErr
    0.33
    比特
    0.33
    urlencoded
    0.33
    Conclu
    0.32
    Activations Density 0.196%

    No Known Activations