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. 93554
    Prev
    Next
    INDEX
    Explanations

    mentions of movies and TV shows along with details about their availability and production

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

    shows, movies, and series

    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
    BASELINE
    -0.36
    Шаг
    -0.34
    tifact
    -0.33
    WithIdentifier
    -0.32
     JTextArea
    -0.32
    XMLSchema
    -0.32
    ebaran
    -0.31
     idéia
    -0.31
     journaux
    -0.31
     Miß
    -0.30
    POSITIVE LOGITS
     streaming
    1.20
     Netflix
    1.14
    Netflix
    1.08
     Streaming
    1.01
     netflix
    1.00
    streaming
    0.95
    Streaming
    0.88
     streamer
    0.84
     streamed
    0.77
     Spotify
    0.76
    Activations Density 0.017%

    No Known Activations