© 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. 7535
    Prev
    Next
    INDEX
    Explanations

    syntax elements and identifiers related to programming and coding structures

    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
    IDE
    -0.64
     IDE
    -0.63
    IDES
    -0.61
     Wikimedijinoj
    -0.57
    IDS
    -0.56
     EconPapers
    -0.55
    IDER
    -0.55
    tvguidetime
    -0.54
     IDS
    -0.54
     RIDE
    -0.53
    POSITIVE LOGITS
     id
    0.92
    id
    0.77
     md
    0.70
    md
    0.69
    sd
    0.68
    cd
    0.67
    hd
    0.66
    bd
    0.65
    ad
    0.64
     od
    0.64
    Activations Density 0.405%

    No Known Activations