© 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. 10941
    Prev
    Next
    INDEX
    Explanations

    code snippets or syntax related to database queries in programming languages

    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
     Routes
    -0.47
     utafitiHapana
    -0.44
    rds
    -0.44
     Ribs
    -0.44
    Rolls
    -0.44
     Lines
    -0.44
     rugs
    -0.43
    recipes
    -0.42
     radi
    -0.42
     Christine
    -0.42
    POSITIVE LOGITS
     row
    1.79
    row
    1.59
    Row
    1.32
     Row
    1.27
     cow
    0.82
     flow
    0.77
    ow
    0.75
    ROW
    0.75
     ow
    0.70
     bow
    0.70
    Activations Density 0.332%

    No Known Activations