© 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. 200
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the past action of using something or occurring events

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

    "used to" or "happen to"

    np_acts-logits-general · gemini-2.0-flash

    used to / happen to

    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
    :✨
    -0.68
     щоб
    -0.63
    endsection
    -0.60
    üyada
    -0.59
    //
    -0.59
    yml
    -0.57
     để
    -0.56
     чтобы
    -0.53
     CanadaChoose
    -0.53
    зулта
    -0.53
    POSITIVE LOGITS
     be
    0.70
    tobe
    0.64
    styleType
    0.61
    ToBe
    0.60
     Gorg
    0.57
    verifyException
    0.57
     '\\;'
    0.57
     být
    0.55
    antly
    0.55
     happen
    0.53
    Activations Density 0.112%

    No Known Activations