© 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. 27-GEMMASCOPE-RES-16K
    6. 8938
    Prev
    Next
    INDEX
    Explanations

    instances of questioning and reasoning in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.76
    NameInMap
    -0.68
     للمعارف
    -0.66
     المعيارى
    -0.60
     AssemblyTitle
    -0.56
    Autoritní
    -0.56
    endforeach
    -0.54
    :✨
    -0.52
    SourceChecksum
    -0.50
    aarrggbb
    -0.50
    POSITIVE LOGITS
     reasons
    1.77
     reason
    1.56
     Reasons
    1.55
    Reasons
    1.49
    reasons
    1.48
    理由
    1.47
     REASONS
    1.40
    Reason
    1.37
    reason
    1.36
    REASONS
    1.33
    Activations Density 0.576%

    No Known Activations