© 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. 10185
    Prev
    Next
    INDEX
    Explanations

    references to film production techniques and analysis

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

    Camera shots or cuts

    np_acts-logits-general · gemini-2.0-flash

    filming and editing shots

    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
    complexType
    -0.90
    createCanvas
    -0.75
    setVerticalGroup
    -0.71
     Roskov
    -0.70
    principalTable
    -0.65
    AndEndTag
    -0.65
     flexível
    -0.65
     AssemblyCulture
    -0.65
    UnitTesting
    -0.61
     virulence
    -0.61
    POSITIVE LOGITS
     camera
    1.20
    camera
    1.00
     footage
    0.98
     shots
    0.93
     montage
    0.92
     shot
    0.91
     kamera
    0.90
     Camera
    0.89
    Camera
    0.87
     cut
    0.85
    Activations Density 0.327%

    No Known Activations