© 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. 11123
    Prev
    Next
    INDEX
    Explanations

    function calls and nested expressions in programming code

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

    Code with parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    special characters and code delimiters

    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
    .
    -0.54
    </i>
    -0.51
     as
    -0.49
     he
    -0.49
    ’
    -0.48
     we
    -0.47
     bar
    -0.47
    <b>
    -0.45
    -
    -0.45
    …
    -0.45
    POSITIVE LOGITS
     myſelf
    1.21
    曖昧さ回避
    1.14
     >=",
    1.12
     Monfieur
    1.09
    yntaxException
    1.09
     Efq
    1.04
     poffible
    1.04
     متعلقه
    1.04
     purpoſe
    1.03
     itſelf
    1.03
    Activations Density 0.363%

    No Known Activations