© 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. 38-GEMMASCOPE-RES-16K
    11. 9567
    Prev
    Next
    INDEX
    Explanations

    specific geographic or place-related terms and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.39
     Reich
    -0.33
    StandardCharsets
    -0.33
     Rech
    -0.33
    StructEnd
    -0.31
    Reich
    -0.30
    WhereInput
    -0.30
     Reversible
    -0.30
    rays
    -0.29
     Regener
    -0.29
    POSITIVE LOGITS
     ro
    2.23
     Ro
    1.98
    Ro
    1.84
     RO
    1.81
    RO
    1.65
    ro
    1.56
     Ро
    1.55
     ROD
    1.53
     ро
    1.52
     Rod
    1.48
    Activations Density 2.205%

    No Known Activations