© 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. 14601
    Prev
    Next
    INDEX
    Explanations

    references to prior knowledge or existing conditions

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

    "Already" at the start of a sentence

    np_acts-logits-general · gemini-2.0-flash

    already marking a past state or completion

    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
    still
    -0.89
     todavía
    -0.85
     aún
    -0.83
     still
    -0.82
     fortfarande
    -0.81
     هنوز
    -0.80
     ainda
    -0.78
     also
    -0.78
     ešte
    -0.77
    未だ
    -0.77
    POSITIVE LOGITS
     BoxFit
    0.75
    RenderAtEndOf
    0.74
     begun
    0.74
    AsUp
    0.72
     فريبيس
    0.71
    IsMutable
    0.69
    دانشنامهٔ
    0.69
    tellen
    0.69
     ProtoMessage
    0.67
    protoc
    0.65
    Activations Density 0.089%

    No Known Activations