© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15345
    Prev
    Next
    INDEX
    Explanations

    mathematical structures related to arrays or matrices in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     te
    -0.47
    .
    -0.44
     
    -0.44
    hetically
    -0.43
     ci
    -0.43
     D
    -0.43
     Association
    -0.43
    ci
    -0.43
     En
    -0.42
    -
    -0.42
    POSITIVE LOGITS
     ModelExpression
    0.92
     Roskov
    0.88
     الرياضيه
    0.88
     tartalomajánló
    0.85
    GEBURTSDATUM
    0.79
     endblock
    0.77
    Portale
    0.77
     للاسماء
    0.75
     CURIAM
    0.75
    EndGlobalSection
    0.74
    Activations Density 0.133%

    No Known Activations