© 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. 6019
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to crimes and offenses

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

    criminal charges and convictions

    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
    TypedDataSet
    -0.47
    цездатний
    -0.46
    esserts
    -0.42
    webElementXpaths
    -0.41
    ungkan
    -0.41
    uffy
    -0.40
    amodel
    -0.39
     reality
    -0.39
    quitous
    -0.39
     createState
    -0.39
    POSITIVE LOGITS
     charges
    0.73
     Charges
    0.65
     agrav
    0.58
    Charges
    0.56
     charge
    0.54
    罪
    0.53
     stemming
    0.50
    charges
    0.48
     occafion
    0.47
     Counts
    0.46
    Activations Density 0.073%

    No Known Activations