© 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. 37-GEMMASCOPE-RES-16K
    11. 5816
    Prev
    Next
    INDEX
    Explanations

    references to specific methods or techniques in research and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.63
    AndEndTag
    -0.57
    httphttps
    -0.56
    richTextPanel
    -0.55
    WarningLevel
    -0.50
     Wiktionnaire
    -0.49
    adaptiveStyles
    -0.49
    enumii
    -0.48
     Vikipedi
    -0.48
    rungsseite
    -0.48
    POSITIVE LOGITS
    afficheront
    0.40
    jarah
    0.39
     contemporaine
    0.34
     ň
    0.34
     Отечественной
    0.34
    ruik
    0.34
    isBlank
    0.33
     Públicas
    0.33
    carina
    0.33
    ilia
    0.31
    Activations Density 0.913%

    No Known Activations