Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14680
    Prev
    Next
    INDEX
    Explanations

    overall evaluative statements or summaries regarding various topics

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

    Preceding "overall" or "Overall"

    np_acts-logits-general · gemini-2.0-flash

    overall summary or conclusion

    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
     selanjutnya
    -0.63
    previously
    -0.62
     subsequently
    -0.62
     berikutnya
    -0.60
    tidine
    -0.57
    今度
    -0.57
     previously
    -0.57
    中には
    -0.56
     originally
    -0.56
    اتي
    -0.56
    POSITIVE LOGITS
     speaking
    1.04
     betrachtet
    0.85
    而言
    0.84
    speaking
    0.80
     gesehen
    0.79
    來說
    0.78
    来说
    0.74
     parlando
    0.73
     gezien
    0.73
     hablando
    0.70
    Activations Density 0.174%

    No Known Activations