© 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. 38508
    Prev
    Next
    INDEX
    Explanations

    references to streaming platforms and social interactions

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

    Twitch streaming

    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
    ChildScrollView
    -0.52
    GeoNames
    -0.50
     Bupati
    -0.50
    boutin
    -0.49
     wikipagina
    -0.49
     civile
    -0.49
    DataAnnotations
    -0.48
     FACEBOOK
    -0.47
    migrationBuilder
    -0.47
     demurrer
    -0.47
    POSITIVE LOGITS
     Twitch
    0.78
    Twitch
    0.61
     streamers
    0.57
     twitch
    0.55
     streamer
    0.53
    twitch
    0.53
     viewers
    0.49
     stream
    0.48
     Stream
    0.47
     viewer
    0.45
    Activations Density 0.010%

    No Known Activations