© 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. 14-GEMMASCOPE-RES-16K
    11. 10254
    Prev
    Next
    INDEX
    Explanations

    punctuation and numerical characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     désolés
    -0.52
     who
    -0.47
     Dr
    -0.46
     çık
    -0.42
    byen
    -0.41
     ơn
    -0.41
    who
    -0.39
    getActive
    -0.39
     G
    -0.38
     colore
    -0.38
    POSITIVE LOGITS
    انيف
    0.95
    ViewFeatures
    0.84
    IVEREF
    0.83
    titleMargin
    0.82
    providedIn
    0.81
    setVerticalGroup
    0.81
     Roskov
    0.80
     дописавши
    0.80
    VersionUID
    0.79
    RuleContext
    0.78
    Activations Density 0.304%

    No Known Activations