© 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. 1-GEMMASCOPE-RES-16K
    11. 13191
    Prev
    Next
    INDEX
    Explanations

    terms related to spells, particularly those involving whips and magical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndice
    -0.68
    orsese
    -0.65
    WebElementEntity
    -0.65
    TintMode
    -0.64
    دانشنامهٔ
    -0.59
    شوف
    -0.58
     contextLoads
    -0.57
    sery
    -0.57
    bleshooting
    -0.56
    TokenNameLBRACE
    -0.56
    POSITIVE LOGITS
    ollectionView
    0.72
     whips
    0.67
    bow
    0.60
     StatelessWidget
    0.59
    whip
    0.58
    ồn
    0.56
     Buddhist
    0.55
    Pod
    0.55
     bowing
    0.54
     Hawthorne
    0.53
    Activations Density 2.167%

    No Known Activations