© 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. 31-GEMMASCOPE-RES-131K
    11. 24484
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and references to legal proceedings

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

    incidents or instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.47
    lapsingToolbar
    -0.45
    AddTagHelper
    -0.44
    Aktualisiert
    -0.43
    ніципалі
    -0.42
    (!__
    -0.42
    awakeFromNib
    -0.39
    MessageTagHelper
    -0.39
    hasilkan
    -0.38
    Personensuche
    -0.38
    POSITIVE LOGITS
     incident
    2.55
     incidents
    2.44
     Incident
    2.09
    incident
    2.06
     Incidents
    2.05
     incidente
    1.94
     kejadian
    1.68
    Incident
    1.66
    事件
    1.61
     घटना
    1.56
    Activations Density 0.331%

    No Known Activations