© 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. 20-GEMMASCOPE-RES-16K
    11. 6875
    Prev
    Next
    INDEX
    Explanations

    references to formal processes and documentation

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

    after a period or punctuation, indicating a sentence start

    np_acts-logits-general · gemini-2.0-flash

    events and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ScopeManager
    -0.83
     propOrder
    -0.78
    RenderAtEndOf
    -0.77
     CreateTagHelper
    -0.74
    ########.
    -0.69
    WebElementEntity
    -0.67
    mergeFrom
    -0.66
    DockStyle
    -0.65
    SharedCtor
    -0.64
     <<<<<<<<<<<<<<
    -0.63
    POSITIVE LOGITS
     became
    0.90
     arrives
    0.87
     came
    0.86
     becomes
    0.84
     comes
    0.83
     began
    0.77
     become
    0.76
     مباشرة
    0.75
     has
    0.73
     expires
    0.72
    Activations Density 0.227%

    No Known Activations