© 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. 37-GEMMASCOPE-RES-16K
    11. 3062
    Prev
    Next
    INDEX
    Explanations

    coding-related components, specifically focusing on function definitions and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zijne
    -0.66
     surla
    -0.65
     nahilalakip
    -0.63
     CURIAM
    -0.62
    <?
    -0.60
     mères
    -0.59
     CanadaChoose
    -0.58
    ſchaft
    -0.58
     desmotivaciones
    -0.54
     wireType
    -0.53
    POSITIVE LOGITS
    atguigu
    0.45
    ruik
    0.40
    setof
    0.39
    VertexAttrib
    0.38
    ㅣ
    0.37
     becas
    0.35
     Adress
    0.35
     GenerationType
    0.35
     adress
    0.35
     thier
    0.35
    Activations Density 0.098%

    No Known Activations