© 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. 22-GEMMASCOPE-RES-16K
    11. 9058
    Prev
    Next
    INDEX
    Explanations

    code syntax elements, particularly backticks and regex patterns

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

    Code snippets with backticks

    np_acts-logits-general · gemini-2.0-flash

    archaic long s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.82
    ';
    -0.77
    ViewFeatures
    -0.77
    •••
    -0.69
    </strong>
    -0.69
     he
    -0.69
    newArrayList
    -0.67
     Am
    -0.67
    ("");
    -0.66
    __);
    -0.66
    POSITIVE LOGITS
    ſelf
    1.14
     myſelf
    1.07
    ſelves
    1.06
     uſed
    1.03
     ſever
    1.01
    .`
    1.01
     itſelf
    0.99
     reaſon
    0.98
    "`
    0.97
     greateſt
    0.94
    Activations Density 0.206%

    No Known Activations