© 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. 4402
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and vector expressions

    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
    ConstraintMaker
    -0.48
    WriteBarrier
    -0.44
     Gaps
    -0.43
    gaps
    -0.42
    BoxShadow
    -0.40
     gaps
    -0.40
     intptr
    -0.39
    ьаж
    -0.39
    trucks
    -0.38
    ➟
    -0.37
    POSITIVE LOGITS
     resourceCulture
    0.50
    berdayakan
    0.50
    Eksteraj
    0.49
    RTSC
    0.46
    UpdateCommand
    0.44
    spunkt
    0.42
    IDL
    0.41
    LLocation
    0.41
     uppdater
    0.41
     $|\
    0.40
    Activations Density 0.625%

    No Known Activations