© 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. 110862
    Prev
    Next
    INDEX
    Explanations

    programming or plotting functions related to data visualization

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

    plot symbols and colors

    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
     wrinkles
    -0.49
     lines
    -0.39
     creases
    -0.38
    一条
    -0.34
    一條
    -0.32
    ChildScrollView
    -0.32
    AndEndTag
    -0.32
     dividers
    -0.32
     cracks
    -0.31
     Abschnitt
    -0.30
    POSITIVE LOGITS
    scatter
    0.85
     scatter
    0.84
     Scatter
    0.82
     marker
    0.79
    Marker
    0.76
     markers
    0.75
    marker
    0.73
    Scatter
    0.73
     Marker
    0.72
     symbols
    0.71
    Activations Density 0.107%

    No Known Activations