© 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. 250
    Prev
    Next
    INDEX
    Explanations

    verbs indicating observation or passive participation in events

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

    watching or observing

    np_acts-logits-general · gemini-2.0-flash

    watching and observing

    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
    -0.56
     provisoire
    -0.50
     nonUne
    -0.49
    lineTo
    -0.46
     BoxDecoration
    -0.46
    MigrationBuilder
    -0.45
    multirow
    -0.45
    Παραπομπές
    -0.44
     coffre
    -0.43
    reszcie
    -0.42
    POSITIVE LOGITS
     watching
    2.32
     watch
    2.08
     Watching
    2.05
    Watching
    2.01
     watched
    2.00
    watching
    1.99
     watches
    1.87
     WATCH
    1.82
     Watch
    1.80
    watch
    1.80
    Activations Density 0.256%

    No Known Activations