© 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. 10-GEMMASCOPE-RES-16K
    11. 7213
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts involving statistics or rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
    脚注の使い方
    -0.43
    SharedCtor
    -0.39
    providedIn
    -0.38
     externos
    -0.38
    archiviato
    -0.37
    뀔
    -0.36
     broche
    -0.36
    .*")]
    -0.36
    LookAnd
    -0.35
    EndGlobalSection
    -0.33
    POSITIVE LOGITS
     GenerationType
    0.52
    resar
    0.47
     equivalent
    0.47
    Хьажоргаш
    0.46
    equivalent
    0.46
    DIPSETTING
    0.46
     ritratto
    0.45
    Equivalent
    0.44
    careous
    0.42
     compares
    0.42
    Activations Density 0.778%

    No Known Activations