© 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. 9-GEMMASCOPE-RES-16K
    11. 1643
    Prev
    Next
    INDEX
    Explanations

    phrases involving actions related to individuals and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.88
     Efq
    -0.80
     (\<
    -0.73
     iſt
    -0.72
     Reſ
    -0.71
     Diſ
    -0.71
     stiefel
    -0.70
     Majefty
    -0.70
     Beſ
    -0.69
     reaſon
    -0.69
    POSITIVE LOGITS
     را
    0.74
    ceğini
    0.73
    devamını
    0.70
    ığını
    0.70
    larını
    0.69
    音を
    0.69
    MENAFN
    0.68
    lerini
    0.67
    meyi
    0.67
    ätä
    0.66
    Activations Density 0.052%

    No Known Activations