© 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. 17-GEMMASCOPE-RES-16K
    11. 9290
    Prev
    Next
    INDEX
    Explanations

    sentiments related to excitement and transition, particularly in the context of fashion and seasonal changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guien
    -0.59
    例文帳に追加
    -0.57
    ندما
    -0.52
     Sangat
    -0.52
     politiet
    -0.52
    ękuję
    -0.49
     rerum
    -0.49
    expandindo
    -0.49
    maktadır
    -0.48
    Cordialement
    -0.47
    POSITIVE LOGITS
     celebs
    0.74
     swears
    0.73
     udah
    0.72
     BFF
    0.69
     faves
    0.69
     swear
    0.67
     luxe
    0.67
     gotta
    0.67
     fave
    0.66
     bae
    0.65
    Activations Density 0.266%

    No Known Activations