© 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. 15415
    Prev
    Next
    INDEX
    Explanations

    sequences of repeated or similar whitespace characters

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

    Numbers within specific contexts

    np_acts-logits-general · gemini-2.0-flash

    anything complex

    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
     to
    -0.59
     Betracht
    -0.58
     in
    -0.57
     th
    -0.56
     di
    -0.55
     li
    -0.55
     im
    -0.55
     ${
    -0.55
     t
    -0.54
     k
    -0.53
    POSITIVE LOGITS
     itſelf
    1.43
     myſelf
    1.37
     ſtate
    1.26
     Anſ
    1.21
     greateſt
    1.21
     Efq
    1.18
     doubtnut
    1.17
     pleaſure
    1.17
     ſche
    1.17
     ſeveral
    1.17
    Activations Density 1.153%

    No Known Activations