© 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. 16-GEMMASCOPE-RES-16K
    11. 5390
    Prev
    Next
    INDEX
    Explanations

    elements related to formal documents and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Formal documents

    np_acts-logits-general · gemini-2.0-flash

    official documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hasNext
    -0.48
    FXML
    -0.43
    clearTimeout
    -0.42
    HasColumnName
    -0.42
    つぶ
    -0.41
    flexDirection
    -0.41
    меры
    -0.41
    vaal
    -0.39
    providedIn
    -0.39
     durumda
    -0.39
    POSITIVE LOGITS
     sheet
    0.79
     rédig
    0.78
     sheets
    0.76
    setVerticalGroup
    0.71
    ViewFeatures
    0.71
     issued
    0.70
    RenderAtEndOf
    0.70
     ✭✭
    0.70
     detailing
    0.70
    heets
    0.69
    Activations Density 1.210%

    No Known Activations