© 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. 2786
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors related to size and variety

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

    Comes before "range" or "variety"

    np_acts-logits-general · gemini-2.0-flash

    wide variety or range

    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
    contentLoaded
    -1.08
    MigrationBuilder
    -0.99
    TypedDataSet
    -0.95
     חיצוניים
    -0.89
    GEBURTSDATUM
    -0.86
    RegressionTest
    -0.85
     CanadaChoose
    -0.85
    afficheront
    -0.85
    ագրություններ
    -0.84
    ReusableCell
    -0.84
    POSITIVE LOGITS
     wide
    0.82
    componentWill
    0.62
     broad
    0.61
     host
    0.57
     select
    0.56
     wider
    0.55
     large
    0.55
     growing
    0.52
     selection
    0.51
     ver
    0.51
    Activations Density 0.188%

    No Known Activations