© 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. 4118
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistics related to demographics, programs, or resources

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

    Large numerical values

    np_acts-logits-general · gemini-2.0-flash

    numerical quantities and scales

    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
     pouvoirs
    -0.57
    setFlags
    -0.54
     للمعارف
    -0.52
     NSError
    -0.52
     kasarigan
    -0.50
     besoins
    -0.50
    ))))
    -0.49
    RunWith
    -0.49
    ))),
    -0.48
    atiles
    -0.48
    POSITIVE LOGITS
     million
    1.28
     thousand
    1.26
    thousand
    0.97
     thousands
    0.97
     billion
    0.96
     MILLION
    0.95
     hundred
    0.93
    million
    0.93
     THOUS
    0.90
     different
    0.87
    Activations Density 0.354%

    No Known Activations