© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12628
    Prev
    Next
    INDEX
    Explanations

    elements related to suspense and tension in storytelling

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

    Movie scores and soundtracks

    np_acts-logits-general · gemini-2.0-flash

    music, scores, themes, soundtracks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.62
    struktion
    -0.59
    Tour
    -0.56
     Infórmanos
    -0.56
    TOUR
    -0.55
     propOrder
    -0.55
     pinta
    -0.55
     confronti
    -0.55
     Tour
    -0.54
    tour
    -0.54
    POSITIVE LOGITS
     soundtrack
    1.30
     theme
    1.08
     score
    1.04
    Soundtrack
    1.01
     trilha
    0.99
     Soundtrack
    0.97
     OST
    0.94
     Theme
    0.93
     background
    0.90
     music
    0.90
    Activations Density 0.137%

    No Known Activations