© 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. 31-GEMMASCOPE-RES-131K
    6. 21747
    Prev
    Next
    INDEX
    Explanations

    references to physical movement and locations

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

    upstairs and downstairs movement

    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
    Hochspringen
    -0.33
    AndEndTag
    -0.32
    सन्दर्भ
    -0.31
     Мексичка
    -0.30
     entanto
    -0.30
    原始内容存档于
    -0.30
    haikusbot
    -0.29
     hombro
    -0.29
    __(
    -0.27
    ⓧ
    -0.27
    POSITIVE LOGITS
     downstairs
    1.40
     upstairs
    1.39
    Upstairs
    1.10
     downstream
    0.95
     upstream
    0.91
    stairs
    0.85
     downtown
    0.85
     Upstream
    0.81
     Down
    0.81
    upstream
    0.79
    Activations Density 0.167%

    No Known Activations