© 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. 20-GEMMASCOPE-RES-131K
    6. 94852
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fine" in various contexts

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

    fine descriptions

    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
     McLeod
    -0.65
    losigkeit
    -0.59
     mochila
    -0.59
    accountId
    -0.58
     gravidez
    -0.57
    unicip
    -0.56
    Syst
    -0.56
    囔
    -0.56
    Asoci
    -0.55
    versary
    -0.55
    POSITIVE LOGITS
    Fine
    1.11
     Fine
    1.06
    fine
    1.04
     fine
    1.02
     FINE
    0.97
    FINE
    0.96
     fines
    0.65
     Fein
    0.65
     Fines
    0.64
     finos
    0.64
    Activations Density 0.011%

    No Known Activations