© 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. 36-GEMMASCOPE-RES-16K
    11. 12670
    Prev
    Next
    INDEX
    Explanations

    lines of code and programming-related constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.35
    XtraReports
    -0.33
    formazioni
    -0.33
    parsedMessage
    -0.32
     ModelExpression
    -0.31
     صوتيه
    -0.31
     bumbu
    -0.30
     كومونز
    -0.30
     ruinas
    -0.29
    Personendaten
    -0.29
    POSITIVE LOGITS
     @
    3.22
    @
    2.94
    (@
    2.42
     (@
    2.30
    ,@
    2.23
    .@
    2.19
    =@
    2.17
    -@
    2.09
    :@
    2.08
     [@
    2.03
    Activations Density 1.491%

    No Known Activations