© 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. 8220
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols typically used in programming or scripting contexts

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

    Code delimiters or parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses and brackets

    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
    __*/
    -0.89
    ✭✭
    -0.81
    saraba
    -0.77
    GEBURTS
    -0.77
    دانشنامهٔ
    -0.73
    DockStyle
    -0.71
    )");
    -0.71
    UserScript
    -0.70
     vuitton
    -0.70
     كومونز
    -0.69
    POSITIVE LOGITS
    ,
    0.67
     then
    0.67
    .
    0.65
    ↵
    0.64
     as
    0.61
    ↵↵
    0.61
    :
    0.57
     and
    0.56
     ||
    0.56
     return
    0.56
    Activations Density 0.614%

    No Known Activations