© 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. 65260
    Prev
    Next
    INDEX
    Explanations

    references to specific motorcycle brands and models

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

    Kawasaki motorcycles or engines

    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
    RequestOptions
    -0.40
    ToBounds
    -0.40
    gwick
    -0.39
    Diwedd
    -0.38
     Flag
    -0.38
    mögens
    -0.38
     المعيارى
    -0.38
     GRID
    -0.37
    :+:
    -0.37
    ModelAdmin
    -0.37
    POSITIVE LOGITS
     motorcycles
    0.62
     machinery
    0.59
     Maschinen
    0.58
     engines
    0.56
     mesin
    0.54
     machines
    0.54
     maquinaria
    0.53
    machinery
    0.52
     motorcycle
    0.52
     machine
    0.51
    Activations Density 0.039%

    No Known Activations