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

    Neuronpedia

    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. 2879
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or special formatting

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

    Numbers or symbols, often within parentheses

    np_acts-logits-general · gemini-2.0-flash

    biological/scientific sex or specimens

    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
     near
    -0.74
    ed
    -0.71
     just
    -0.68
    ven
    -0.68
    to
    -0.67
    al
    -0.67
    es
    -0.66
     ressemb
    -0.65
    and
    -0.64
    red
    -0.64
    POSITIVE LOGITS
    tagHelperRunner
    0.96
     cherchés
    0.87
     propOrder
    0.78
    ThroughAttribute
    0.75
    GraphicsUnit
    0.71
    ")));
    0.70
     متعلقه
    0.70
     Taktlose
    0.69
    цездатний
    0.67
     يتيمه
    0.66
    Activations Density 0.001%

    No Known Activations