© 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. 10534
    Prev
    Next
    INDEX
    Explanations

    phrases indicating early intervention and identification of conditions or outcomes

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

    "early" or time before schedule

    np_acts-logits-general · gemini-2.0-flash

    early or sooner

    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
    fortawesome
    -0.45
    żesz
    -0.45
    HtmlAttribute
    -0.45
    клопе
    -0.43
    HttpPost
    -0.43
    plyr
    -0.42
     الحره
    -0.42
    soort
    -0.41
     الاطلاع
    -0.41
    lético
    -0.40
    POSITIVE LOGITS
     early
    3.15
    early
    2.85
    Early
    2.73
     Early
    2.63
     EARLY
    2.62
     earlier
    2.46
    EARLY
    2.42
    earlier
    2.16
     earliest
    2.16
     sooner
    2.12
    Activations Density 0.668%

    No Known Activations