© 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. 33-GEMMASCOPE-RES-16K
    11. 12706
    Prev
    Next
    INDEX
    Explanations

    declarations of final static variables in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finally
    -0.56
    EndContext
    -0.56
    出版年
    -0.55
     arşivlendi
    -0.51
    finally
    -0.46
    MessageState
    -0.45
     enfin
    -0.44
    öglichkeiten
    -0.43
     CanadaChoose
    -0.43
     akhirnya
    -0.43
    POSITIVE LOGITS
     int
    0.47
    documentElement
    0.43
    ValueStyle
    0.43
    }{*}{
    0.42
    setCustom
    0.41
    AMILTON
    0.40
    createNew
    0.40
    AutoScaleMode
    0.39
    Viited
    0.38
     SafeMath
    0.38
    Activations Density 0.034%

    No Known Activations