© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6673
    Prev
    Next
    INDEX
    Explanations

    instances of non-interactive code elements or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.50
    setVerticalGroup
    -0.49
     sienten
    -0.46
     '{@
    -0.46
     erila
    -0.44
     compéti
    -0.44
     vertrouwen
    -0.44
    breng
    -0.43
     olsun
    -0.43
    исленность
    -0.43
    POSITIVE LOGITS
    httphttps
    0.63
     ?)
    0.57
    TagMode
    0.56
    ).)
    0.56
    ?),
    0.56
    ?).
    0.54
    transQ
    0.54
    ??)
    0.52
    !!)
    0.52
    ?)
    0.50
    Activations Density 0.943%

    No Known Activations