© 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. 94744
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases that indicate legal or procedural actions in the context of cases and statements

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

    otherwise reduce X

    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
    InvalidProtocol
    -0.55
    LabelTagHelper
    -0.50
    UrlResolution
    -0.48
    Cyfeiriadau
    -0.46
     nonatomic
    -0.44
     ligiloj
    -0.44
    ніципалі
    -0.40
    Naissance
    -0.40
    AccessorTable
    -0.40
    Callable
    -0.40
    POSITIVE LOGITS
     drapeau
    0.40
     cuchara
    0.39
    ])).
    0.38
    
    0.38
    なります
    0.36
     activer
    0.36
    persion
    0.36
     driven
    0.36
     fijo
    0.35
     pasillo
    0.35
    Activations Density 0.152%

    No Known Activations