© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3470
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data or parameters in document structures

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

    Characters following a symbol

    np_acts-logits-general · gemini-2.0-flash

    STAT, typename, stack, mathematical symbols

    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
    —
    -0.71
    --
    -0.70
    Hentet
    -0.68
    </u>
    -0.67
    "
    -0.59
    ”
    -0.57
    !
    -0.53
    .
    -0.53
    </b>
    -0.52
    "--
    -0.52
    POSITIVE LOGITS
    OGND
    0.84
    IntoConstraints
    0.81
     Exacts
    0.80
    enumi
    0.74
    المكان
    0.73
     itſelf
    0.70
     fieldNum
    0.70
     فريبيس
    0.68
    []
    0.68
     myſelf
    0.67
    Activations Density 3.814%

    No Known Activations