© 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. 20-GEMMASCOPE-RES-16K
    11. 15748
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to quantitative regression analysis and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endmodule
    -0.34
     يتيمه
    -0.32
     lòng
    -0.31
    deburg
    -0.31
    ско
    -0.29
    ĝo
    -0.29
    findpost
    -0.29
    キャンセル
    -0.29
    FormBorderStyle
    -0.28
     profondità
    -0.28
    POSITIVE LOGITS
    NameInMap
    0.65
    Geplaatst
    0.63
     ब्रेकडाउन
    0.62
     nakalista
    0.58
    новништво
    0.57
    出版年
    0.55
     visual
    0.53
    Vidite
    0.53
     visualiser
    0.52
     photos
    0.50
    Activations Density 0.562%

    No Known Activations