© 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. 8364
    Prev
    Next
    INDEX
    Explanations

    formatting elements and structure in scientific or technical documents

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

    LaTeX or code snippets

    np_acts-logits-general · gemini-2.0-flash

    function calls and code blocks

    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
     unknownFields
    -0.79
    __((
    -0.70
    Diwedd
    -0.68
    Personensuche
    -0.64
    endregion
    -0.62
    зулта
    -0.60
    Rüyada
    -0.59
    evos
    -0.58
    rrggbb
    -0.57
     estimés
    -0.57
    POSITIVE LOGITS
     }}$}
    0.58
    ThroughAttribute
    0.58
    DotNetBar
    0.53
    })*/
    0.51
    localVar
    0.49
    __':
    0.47
    ')";
    0.47
    ագրություններ
    0.47
     
    0.47
    });*/
    0.46
    Activations Density 0.073%

    No Known Activations