© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8293
    Prev
    Next
    INDEX
    Explanations

    references to CSS and JavaScript resources in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beobachtung
    -0.48
     miniaturka
    -0.47
    ิลปะ
    -0.46
     Beobach
    -0.46
    nocześnie
    -0.46
     mantequilla
    -0.45
     Méndez
    -0.44
     tesettür
    -0.44
     Moskau
    -0.44
     Italij
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.93
    RenderAtEndOf
    0.83
    DockStyle
    0.78
    ########.
    0.78
    MessageTagHelper
    0.77
    IsMutable
    0.73
    BeginContext
    0.72
    __*/
    0.71
     GenerationType
    0.69
     defaultstate
    0.69
    Activations Density 0.449%

    No Known Activations