© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6703
    Prev
    Next
    INDEX
    Explanations

    words related to film titles and movie discussions

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

    Movie/film mentions

    np_acts-logits-general · gemini-2.0-flash

    movie titles

    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
    EndContext
    -0.65
     Hermitage
    -0.60
     Crimean
    -0.57
    UnsafeEnabled
    -0.57
     تانيه
    -0.56
     MenuView
    -0.55
    otone
    -0.55
     betweenstory
    -0.55
     Carcass
    -0.55
     opium
    -0.54
    POSITIVE LOGITS
    migrationBuilder
    0.56
     movie
    0.54
    Filmographie
    0.52
    ˏ
    0.48
     Remo
    0.47
    💼
    0.46
    ATILE
    0.46
    例文帳に追加
    0.45
     movies
    0.44
     doanh
    0.44
    Activations Density 0.136%

    No Known Activations