© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 637
    Prev
    Next
    INDEX
    Explanations

    references and citations in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.57
     nahilalakip
    -0.43
     hikariConfig
    -0.43
    endcsname
    -0.40
     Italijanski
    -0.40
    TintMode
    -0.39
     detailsNormal
    -0.38
    XtraReports
    -0.38
    WriteLiteral
    -0.38
    HasIndex
    -0.37
    POSITIVE LOGITS
     e
    2.88
     eg
    1.86
    e
    1.48
    eg
    1.27
     např
    1.20
     например
    1.12
     Eg
    1.04
     bijvoorbeeld
    1.02
    Eg
    1.00
     е
    1.00
    Activations Density 2.199%

    No Known Activations