© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2313
    Prev
    Next
    INDEX
    Explanations

    features related to grip and traction in various conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openConnection
    -0.65
     Jefus
    -0.63
     anſ
    -0.61
     BoxDecoration
    -0.59
    Démographie
    -0.59
     Shakspeare
    -0.59
    PendingIntent
    -0.57
    apimachinery
    -0.57
     fevere
    -0.56
     reafon
    -0.55
    POSITIVE LOGITS
    lippery
    0.61
     propOrder
    0.61
     slippery
    0.60
    detectChanges
    0.49
    KommentareTeilen
    0.49
     Traction
    0.49
    rawQuery
    0.49
     Friction
    0.48
     communiquez
    0.48
    فيذ
    0.47
    Activations Density 0.404%

    No Known Activations