Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 64643
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and their changes over time

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

    environmental issues and consequences

    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
     personal
    -0.40
     staff
    -0.33
    flex
    -0.33
     للاسماء
    -0.32
     giác
    -0.32
     accessories
    -0.32
     special
    -0.31
     cros
    -0.30
     co
    -0.30
     handling
    -0.30
    POSITIVE LOGITS
    UrlResolution
    0.81
     devastation
    0.73
     ecológico
    0.72
     pollution
    0.71
     deforestation
    0.71
     erosion
    0.71
     droughts
    0.70
     irrigation
    0.70
    Pollution
    0.70
    RenderAtEndOf
    0.68
    Activations Density 0.081%

    No Known Activations