© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 14206
    Prev
    Next
    INDEX
    Explanations

    code-related structural elements and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enheim
    -0.41
    hein
    -0.40
    anabe
    -0.40
    savefig
    -0.39
    addVertex
    -0.39
    mekte
    -0.38
    istem
    -0.38
    naire
    -0.38
     sili
    -0.37
    deira
    -0.37
    POSITIVE LOGITS
     AssemblyCulture
    0.96
     препратки
    0.95
     CreateTagHelper
    0.88
    featureID
    0.88
    endphp
    0.85
    archiviato
    0.83
    enderror
    0.81
    ніципалі
    0.78
     nahilalakip
    0.78
    WriteTagHelper
    0.78
    Activations Density 0.076%

    No Known Activations