© 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. 21-GEMMASCOPE-RES-16K
    11. 12965
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming syntax and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eff
    -0.42
    甲
    -0.41
    ragalactic
    -0.41
     syner
    -0.40
    Hentet
    -0.40
     inse
    -0.40
     Inse
    -0.40
    دانشنامهٔ
    -0.39
     decoder
    -0.38
    ">//
    -0.38
    POSITIVE LOGITS
     estekak
    0.71
     ModelExpression
    0.56
    astify
    0.55
    awtextra
    0.53
     صوتيه
    0.49
     extremos
    0.44
    Välislingid
    0.44
     Wikimedijinoj
    0.44
    DrawerToggle
    0.44
     мәкал
    0.43
    Activations Density 1.239%

    No Known Activations