© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13281
    Prev
    Next
    INDEX
    Explanations

    references to flat surfaces or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.59
    $_['
    -0.57
    最快更新
    -0.56
     czuj
    -0.54
    achios
    -0.54
    ragamo
    -0.53
    ionization
    -0.53
     Weeknd
    -0.53
     voelen
    -0.53
    DataSnapshot
    -0.52
    POSITIVE LOGITS
     Flat
    0.80
     FLAT
    0.79
     flat
    0.76
    Flat
    0.75
    flat
    0.67
     Straight
    0.63
    FLAT
    0.62
     straight
    0.60
     flats
    0.54
     parallel
    0.54
    Activations Density 0.427%

    No Known Activations