© 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. 31-GEMMASCOPE-RES-131K
    6. 11976
    Prev
    Next
    INDEX
    Explanations

    references to legal issues and procedural matters in court cases

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

    reported for the first time

    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
     старости
    -0.34
    šno
    -0.33
     auprès
    -0.32
    ंदीखरीदारी
    -0.32
    xtra
    -0.32
    bcryptjs
    -0.32
    moose
    -0.31
     ECO
    -0.31
    next
    -0.30
    Rinse
    -0.30
    POSITIVE LOGITS
     впервые
    2.13
     erstmals
    1.98
    初めて
    1.83
    首次
    1.66
     first
    1.62
    第一次
    1.53
     popr
    1.52
     впер
    1.46
    初めての
    1.40
     pertama
    1.34
    Activations Density 0.198%

    No Known Activations