© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10391
    Prev
    Next
    INDEX
    Explanations

    references to data structures and unions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cielo
    -0.35
    リエーション
    -0.35
    waitKey
    -0.34
     privilegio
    -0.32
    gång
    -0.32
     financières
    -0.31
     podamos
    -0.30
     destino
    -0.30
     avance
    -0.29
     aim
    -0.28
    POSITIVE LOGITS
    struct
    2.63
     struct
    2.41
     Struct
    1.86
    Struct
    1.73
     structs
    1.63
     STRUCT
    1.48
    STRUCT
    1.46
    structs
    1.44
     structuring
    1.20
    truct
    1.12
    Activations Density 0.102%

    No Known Activations