© 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. 34-GEMMASCOPE-RES-16K
    11. 11687
    Prev
    Next
    INDEX
    Explanations

    punctuation and clauses that highlight pauses or changes in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wobei
    -0.39
     also
    -0.35
    这是
    -0.34
    ,
    -0.34
    timbangan
    -0.34
     whose
    -0.33
    although
    -0.33
     while
    -0.33
     although
    -0.33
     כאשר
    -0.33
    POSITIVE LOGITS
     nahilalakip
    0.91
    ViewImports
    0.77
    ArgsConstructor
    0.70
     appunto
    0.69
    kloped
    0.68
    ResumeLayout
    0.64
    uxxxx
    0.64
    aarrggbb
    0.63
    ImageContext
    0.63
    erçe
    0.61
    Activations Density 0.556%

    No Known Activations