© 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. 7911
    Prev
    Next
    INDEX
    Explanations

    specific descriptive statistics or measurements

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

    Following "at" or similar words

    np_acts-logits-general · gemini-2.0-flash

    capped at, set at, estimated at

    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
    xFFFFFF
    -0.58
     myſelf
    -0.56
     Efq
    -0.54
     leaſt
    -0.53
    fony
    -0.52
     Forumite
    -0.52
     Monfieur
    -0.51
    xFFFFFFFF
    -0.50
    voorbeeld
    -0.50
     $_"
    -0.50
    POSITIVE LOGITS
     at
    1.73
    At
    1.01
     At
    0.99
    at
    0.98
     @
    0.97
    @
    0.79
     tại
    0.79
     ở
    0.78
    Geplaatst
    0.69
     ویکی‌پدی
    0.68
    Activations Density 0.354%

    No Known Activations