© 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. 116984
    Prev
    Next
    INDEX
    Explanations

    terms related to walking and physical activity

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

    walking and trekking

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of walking and related light physical activities, especially in guidance that specifies durations or frequencies.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     мәкал
    -0.65
     EconPapers
    -0.64
    istoitu
    -0.58
     NgModule
    -0.57
     createSlice
    -0.56
     JpaRepository
    -0.56
     NSCoder
    -0.55
    umbing
    -0.54
     initComponents
    -0.54
    sizeCache
    -0.53
    POSITIVE LOGITS
     walking
    0.91
     walks
    0.83
     Spazier
    0.81
     Walking
    0.81
     walk
    0.78
    walking
    0.77
     Walks
    0.76
     walkers
    0.75
    Walking
    0.75
     WALK
    0.71
    Activations Density 0.013%

    No Known Activations