© 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. 10-GEMMASCOPE-RES-16K
    11. 11508
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to programming or computer code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.67
    AllowUser
    -0.40
    jspb
    -0.40
    staticmethod
    -0.38
     بالن
    -0.38
    ↵↵
    -0.38
     }{\
    -0.37
     osi
    -0.37
    PUBLISH
    -0.37
     fæ
    -0.37
    POSITIVE LOGITS
     HasFactory
    0.97
    contentLoaded
    0.84
    -------------</
    0.83
    HandlerContext
    0.81
    afficheront
    0.80
    Autoritní
    0.79
     nakalista
    0.79
     Lightboxes
    0.78
    脚注の使い方
    0.77
    expandindo
    0.76
    Activations Density 0.301%

    No Known Activations