© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10170
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structure in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.89
    UnusedPrivate
    -0.82
    ftagPool
    -0.79
     AspNetCore
    -0.76
     unknownFields
    -0.76
    rungsseite
    -0.74
    ThroughAttribute
    -0.72
     eventdata
    -0.71
     مرئيه
    -0.69
     kaarangay
    -0.68
    POSITIVE LOGITS
    T
    0.34
     pains
    0.34
    merzen
    0.32
    先
    0.30
    Ground
    0.29
    Q
    0.28
    老
    0.28
    Growth
    0.27
    可
    0.27
    žiai
    0.27
    Activations Density 0.124%

    No Known Activations