© 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. 40-GEMMASCOPE-RES-16K
    11. 6223
    Prev
    Next
    INDEX
    Explanations

    key mathematical and programming definitions and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unjuk
    -0.49
    الحياه
    -0.49
    kmäler
    -0.49
    kannya
    -0.48
     linkovi
    -0.48
     nimic
    -0.48
    impôt
    -0.47
    SourceChecksum
    -0.45
    rsiniz
    -0.44
     slutet
    -0.44
    POSITIVE LOGITS
     كومونز
    0.51
     autorytatywna
    0.43
    */
    0.41
    Einzelnachweise
    0.40
    ########.
    0.39
     ͡
    0.38
    TintMode
    0.37
    
    0.37
    waitKey
    0.36
    IBAction
    0.36
    Activations Density 0.490%

    No Known Activations