© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 92663
    Prev
    Next
    INDEX
    Explanations

    terms related to film editing and awards for editing

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

    film and video editing

    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
    AndEndTag
    -0.53
    WebElementEntity
    -0.48
    featureID
    -0.47
     penetrated
    -0.44
     pemer
    -0.42
    balleur
    -0.42
     Penetration
    -0.41
     emiti
    -0.41
     penetration
    -0.40
     péné
    -0.40
    POSITIVE LOGITS
     collage
    0.92
     editing
    0.90
     montage
    0.86
     edit
    0.85
     edits
    0.81
    編集
    0.74
    collage
    0.70
     splicing
    0.70
     Editing
    0.70
    edit
    0.69
    Activations Density 0.048%

    No Known Activations