© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15060
    Prev
    Next
    INDEX
    Explanations

    statistical achievements and honors in sports contexts

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

    Selection to an "All" team

    np_acts-logits-general · gemini-2.0-flash

    all-star, all-tournament, all-century selections

    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
    RegressionTest
    -0.82
     resourceCulture
    -0.78
     onPostExecute
    -0.69
     estekak
    -0.69
    Portale
    -0.66
    waitKey
    -0.63
    SharedDtor
    -0.63
    IVEREF
    -0.63
    Personendaten
    -0.61
    IMPORTED
    -0.61
    POSITIVE LOGITS
     selection
    0.86
     selections
    0.84
     All
    0.81
     selected
    0.74
     Selection
    0.69
     seleção
    0.69
     honor
    0.69
    All
    0.66
     honore
    0.66
     honorable
    0.66
    Activations Density 0.170%

    No Known Activations