© 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. 4-GEMMASCOPE-RES-16K
    11. 15669
    Prev
    Next
    INDEX
    Explanations

    proper nouns and scientific terms related to individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.79
    Παραπομπές
    -0.70
    Tul
    -0.69
     Huskies
    -0.68
     Gong
    -0.68
    켰
    -0.68
    PreferredItem
    -0.67
    perrt
    -0.65
    Digitized
    -0.65
     Kabir
    -0.65
    POSITIVE LOGITS
    SQUARE
    0.84
    rungsseite
    0.80
    oredCriteria
    0.79
    ErrUnexpectedEOF
    0.73
     Trafalgar
    0.72
    stacked
    0.71
     Madeira
    0.70
    ValueStyle
    0.70
     dispo
    0.70
     Daria
    0.69
    Activations Density 9.269%

    No Known Activations