Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22413
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Language keywords, operators, or punctuation that have syntactic significance in programming code, mathematical notation, or configuration files.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.78
    argout
    -0.59
    ItemBackground
    -0.58
     للاسماء
    -0.58
    AndEndTag
    -0.57
     lenker
    -0.56
    enderror
    -0.54
    BeginInit
    -0.53
     المعيارى
    -0.53
    qrstuvwxyz
    -0.52
    POSITIVE LOGITS
     if
    0.49
     whether
    0.41
    if
    0.39
    IfNeeded
    0.39
     jeśli
    0.39
    jspx
    0.35
     если
    0.35
     אם
    0.35
     jeżeli
    0.35
     nếu
    0.34
    Activations Density 0.132%

    No Known Activations