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. 6110
    Prev
    Next
    INDEX
    Explanations

    references to a "main" or "primary" subject or concept within a text

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

    main/primary purpose or reason

    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
    EndTag
    -0.40
     contín
    -0.35
    ectoria
    -0.35
     continuously
    -0.34
     elles
    -0.33
    resulting
    -0.32
     eventuell
    -0.31
    '>{
    -0.31
     resulting
    -0.30
    nipeg
    -0.30
    POSITIVE LOGITS
     reason
    0.81
     purpose
    0.80
     reasons
    0.79
     goals
    0.78
     goal
    0.78
     purposes
    0.76
     objectives
    0.75
     main
    0.72
    principalColumn
    0.69
     motivations
    0.67
    Activations Density 0.025%

    No Known Activations