© 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. 10693
    Prev
    Next
    INDEX
    Explanations

    indicators of statistical analysis in data reporting

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

    Text sections with specific formatting

    np_acts-logits-general · gemini-2.0-flash

    section and figure identifiers

    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
    ніципа
    -0.69
     שוליים
    -0.68
     utafitiHapana
    -0.61
    (!__
    -0.61
    cticut
    -0.58
    참고
    -0.50
    بوابة
    -0.49
     >=",
    -0.48
    gans
    -0.47
    JsonProperty
    -0.47
    POSITIVE LOGITS
    riwal
    0.60
     jsPsych
    0.50
     "..\..\
    0.50
    posedge
    0.49
     gddr
    0.48
     Erle
    0.47
    GeneratedMessage
    0.47
     Polda
    0.47
     KF
    0.46
    ornadas
    0.46
    Activations Density 0.191%

    No Known Activations