© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 17110
    Prev
    Next
    INDEX
    Explanations

    programming syntax and operators related to variables and arithmetic operations

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

    incrementing values

    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
     &___
    -0.63
    
    -0.58
    InjectAttribute
    -0.57
    .*")]
    -0.57
    RuleContext
    -0.54
    fxml
    -0.52
    باردا
    -0.52
    testify
    -0.52
     deſſen
    -0.51
    rencies
    -0.50
    POSITIVE LOGITS
    ++;
    0.52
     ++;
    0.45
     HIGHER
    0.42
    )++;
    0.41
    ++;
    0.41
    higher
    0.40
     higher
    0.40
     Photocase
    0.40
     supérieures
    0.39
    Higher
    0.39
    Activations Density 0.015%

    No Known Activations