© 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. 73578
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions and actions in programming or code-related contexts

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

    can activate conditional checks

    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
     Domínguez
    -0.39
     Sonn
    -0.38
     Scherer
    -0.35
     Marín
    -0.35
     cintas
    -0.34
    alahkan
    -0.34
     Brunner
    -0.33
    dom
    -0.33
     "]";
    -0.33
     Schult
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    0.97
    canActivate
    0.88
    SharedDtor
    0.84
     nahilalakip
    0.69
    parsedMessage
    0.68
     AspNetCore
    0.65
     propOrder
    0.62
     '\\;'
    0.62
    IVEREF
    0.61
    AndEndTag
    0.61
    Activations Density 0.021%

    No Known Activations