© 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. 105996
    Prev
    Next
    INDEX
    Explanations

    parentheses and their associated structures in code-related contexts

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

    code object identifiers

    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
    LookAnd
    -0.50
     ModelExpression
    -0.47
     representations
    -0.46
    adaptiveStyles
    -0.45
     darkness
    -0.44
     representation
    -0.44
    RegressionTest
    -0.43
    ộm
    -0.41
     approximately
    -0.40
     electricity
    -0.40
    POSITIVE LOGITS
    تقاوى
    0.56
     NSCoder
    0.45
    setAdapter
    0.43
     Abp
    0.42
    eryllium
    0.42
    orari
    0.42
    messageInfo
    0.40
    initState
    0.37
    ?}",
    0.37
     esternos
    0.37
    Activations Density 0.010%

    No Known Activations