© 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. 35-GEMMASCOPE-RES-16K
    6. 14299
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and operations, particularly those involving functions and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    G
    -1.14
     G
    -1.12
    GP
    -0.94
    Gs
    -0.93
     GP
    -0.92
     g
    -0.92
    G
    -0.92
     GS
    -0.91
    GC
    -0.88
    GS
    -0.87
    POSITIVE LOGITS
    ſand
    0.30
    руктура
    0.30
     Fä
    0.30
     Maho
    0.29
    FileUpload
    0.28
     Hed
    0.28
     Castello
    0.27
     bếp
    0.27
    Numerade
    0.27
    ToListAsync
    0.27
    Activations Density 1.843%

    No Known Activations