© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102752
    Prev
    Next
    INDEX
    Explanations

    symbols and characters used in programming and mathematical expressions

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

    Simplify bulk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    
    -0.73
     '\\;'
    -0.72
    rungsseite
    -0.66
    findpost
    -0.62
     esternos
    -0.60
    IntoConstraints
    -0.59
    AnimationsModule
    -0.57
    ロウィン
    -0.55
     препратки
    -0.55
     GetEnumerator
    -0.54
    POSITIVE LOGITS
    퓨
    0.29
     olun
    0.29
    <strong>
    0.29
    [toxicity=0]
    0.29
    tagPool
    0.28
     Stärke
    0.28
    <h2>
    0.28
     Sesame
    0.28
    ../
    0.28
    Pros
    0.28
    Activations Density 0.182%

    No Known Activations