© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12098
    Prev
    Next
    INDEX
    Explanations

    queries and references related to procedures, rules, or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.66
    */),
    -0.58
     linkovi
    -0.56
    CppMethod
    -0.55
     ligiloj
    -0.54
    SharedDtor
    -0.52
     levier
    -0.51
    CloseOperation
    -0.51
    (©
    -0.50
     couteau
    -0.50
    POSITIVE LOGITS
    WriteBarrier
    0.44
     liquid
    0.36
     Liquid
    0.34
    起
    0.33
    何と
    0.32
    writeField
    0.31
    先
    0.31
     LIQUID
    0.30
    niająca
    0.30
    findpost
    0.30
    Activations Density 0.289%

    No Known Activations