© 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. 15383
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and nouns related to processes and components in a structured context

    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
     autorytatywna
    -0.91
     NUKAT
    -0.82
    MigrationBuilder
    -0.81
    новниш
    -0.72
    httphttps
    -0.70
    abestanden
    -0.70
    InteropServices
    -0.70
    ieteur
    -0.70
    TagMode
    -0.68
    basicConfig
    -0.67
    POSITIVE LOGITS
     wise
    0.93
    wise
    0.91
    WISE
    0.66
    Wise
    0.63
     Wise
    0.61
     WISE
    0.59
    -
    0.55
     basis
    0.54
     by
    0.53
     after
    0.51
    Activations Density 0.162%

    No Known Activations