© 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. 22-GEMMASCOPE-RES-16K
    11. 14882
    Prev
    Next
    INDEX
    Explanations

    references to specific lines or figures in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    superuser
    -0.43
    ~*~
    -0.43
     spectacular
    -0.42
    appspot
    -0.42
     Campbell
    -0.42
     Carnaval
    -0.41
     Great
    -0.41
    mutlich
    -0.41
     Fabulous
    -0.41
    possum
    -0.41
    POSITIVE LOGITS
    Line
    1.36
     Line
    1.32
     LINE
    1.23
     line
    1.23
    line
    1.22
    LINE
    1.16
    Lines
    1.04
     Lines
    1.04
    lines
    1.02
     LINES
    0.98
    Activations Density 0.152%

    No Known Activations