Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5321
    Prev
    Next
    INDEX
    Explanations

    legal terminology and procedural references related to court filings and motions

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

    writing and filing legal briefs

    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
    insics
    -0.40
    eringer
    -0.39
    SharedCtor
    -0.39
    inherit
    -0.39
    inherits
    -0.39
    ValueStyle
    -0.37
    rungsseite
    -0.36
     '{@
    -0.36
    theit
    -0.35
    hrung
    -0.34
    POSITIVE LOGITS
     submitted
    0.58
     filed
    0.54
     صوتيه
    0.53
     submission
    0.49
     submissions
    0.48
     CURIAM
    0.45
    MethodManager
    0.45
     ویکی‌پدیا
    0.44
     submitting
    0.44
    ✭✭
    0.43
    Activations Density 0.124%

    No Known Activations