© 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. 38-GEMMASCOPE-RES-16K
    11. 15538
    Prev
    Next
    INDEX
    Explanations

    keywords and constructs related to programming and data structure definitions in a coding context, particularly in the domain of Protobuf and API requests

    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
     незавершена
    -0.79
    ########.
    -0.67
     мәкал
    -0.66
    Personendaten
    -0.63
    Spolja
    -0.59
    reste
    -0.59
    halt
    -0.58
    arms
    -0.58
     González
    -0.57
     Hernández
    -0.57
    POSITIVE LOGITS
    toHaveBeenCalled
    0.36
    !*\
    0.32
    IsMutable
    0.29
     
    0.28
     "{\"
    0.27
    ".$_
    0.26
    ))^{
    0.26
    Ent
    0.26
    astéroïdes
    0.25
     المرجع
    0.25
    Activations Density 0.743%

    No Known Activations