© 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. 20-GEMMASCOPE-RES-16K
    11. 5462
    Prev
    Next
    INDEX
    Explanations

    references to scientific papers and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical details in academic papers, especially in computational biology and statistical research.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    the end of academic paper titles, particularly before journal names or citations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referrerpolicy
    -0.87
    IntoConstraints
    -0.81
     nahilalakip
    -0.80
     propOrder
    -0.79
    SourceChecksum
    -0.77
     CURIAM
    -0.77
    DockStyle
    -0.77
     للاسماء
    -0.73
    StructEnd
    -0.71
    aarrggbb
    -0.70
    POSITIVE LOGITS
    The
    0.49
     in
    0.45
     The
    0.43
     International
    0.42
     a
    0.39
    ://
    0.38
    In
    0.38
     
    0.37
     In
    0.36
     research
    0.35
    Activations Density 0.137%

    No Known Activations