© 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. 1985
    Prev
    Next
    INDEX
    Explanations

    expressions of divine support and care

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

    Follows punctuation, conjunctions, or prepositions

    np_acts-logits-general · gemini-2.0-flash

    religious and legal texts

    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
     température
    -0.50
     temperatura
    -0.50
     TEMPERATURE
    -0.49
     temperature
    -0.48
     teneur
    -0.48
     endforeach
    -0.47
     plastiques
    -0.46
     Cells
    -0.46
    Imper
    -0.46
     Temperature
    -0.46
    POSITIVE LOGITS
    RegressionTest
    0.68
     Zion
    0.60
    ']))
    0.57
    jsii
    0.57
    日閲覧
    0.57
    queryInterface
    0.57
    "]));
    0.55
    ionales
    0.55
    ongiorno
    0.54
     wireType
    0.53
    Activations Density 0.066%

    No Known Activations