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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 4170
    Prev
    Next
    INDEX
    Explanations

    components related to data structure operations and variable assignments

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

    Code snippets with quotes or parentheses

    np_acts-logits-general · gemini-2.0-flash

    string literals and code punctuation

    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
     $("<
    -0.70
    $(".
    -0.68
    $("#
    -0.67
     "/")
    -0.64
    ""}
    -0.60
     "",
    -0.60
    OrBuilder
    -0.59
    {"
    -0.58
     ".";
    -0.57
     ")"
    -0.57
    POSITIVE LOGITS
     '
    2.87
     ‘
    2.79
    『
    2.02
    ‘
    1.84
    ='
    1.76
    ('
    1.74
     (‘
    1.70
     ’
    1.63
    、『
    1.60
     ('
    1.60
    Activations Density 0.301%

    No Known Activations