© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10331
    Prev
    Next
    INDEX
    Explanations

    references to rows in structured data or tabular formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     MIGHT
    -0.50
    might
    -0.49
     Schweitzer
    -0.48
    brief
    -0.47
     Spe
    -0.46
    Might
    -0.46
     Sutherland
    -0.45
     Chelsea
    -0.45
     might
    -0.45
    ifndef
    -0.44
    POSITIVE LOGITS
     Rows
    1.14
     numberOfRows
    1.14
     rows
    1.04
    Row
    1.03
     row
    1.03
     Row
    1.02
    setRow
    1.00
    row
    0.93
    getRow
    0.93
    Rows
    0.93
    Activations Density 0.032%

    No Known Activations