© 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. 4969
    Prev
    Next
    INDEX
    Explanations

    programming-related comments and syntax structure

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

    Comments or notes in code

    np_acts-logits-general · gemini-2.0-flash

    we do.

    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
    <eos>
    -0.95
    <strong>
    -0.95
    <b>
    -0.81
    <em>
    -0.74
    <i>
    -0.70
    ”—
    -0.60
    Your
    -0.57
    ↵↵
    -0.57
     your
    -0.56
     ”.
    -0.55
    POSITIVE LOGITS
     FIXME
    0.88
     ourselves
    0.85
     بيها
    0.78
     TODO
    0.77
     HACK
    0.69
     daqui
    0.69
     sanity
    0.69
    cèse
    0.68
    こっち
    0.67
     мәкалә
    0.66
    Activations Density 0.640%

    No Known Activations