© 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. 37-GEMMASCOPE-RES-16K
    6. 3896
    Prev
    Next
    INDEX
    Explanations

    elements related to coding functions and data conversions in a programming context

    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
    <eos>
    -0.39
    デア
    -0.35
     '
    -0.34
    ↵↵
    -0.33
     indeed
    -0.32
     [
    -0.32
     Burn
    -0.32
    maximize
    -0.31
     finally
    -0.30
     rather
    -0.28
    POSITIVE LOGITS
    同じく
    0.93
     Administrativna
    0.92
    GEBURTSDATUM
    0.76
     surla
    0.74
     similarly
    0.72
    出版年
    0.71
     Paglinawan
    0.71
    
    0.69
     ditto
    0.69
     igualmente
    0.67
    Activations Density 2.746%

    No Known Activations