© 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. 14955
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming structures related to coordinates and frames

    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
     role
    -0.34
    libft
    -0.33
    avedra
    -0.32
     relâche
    -0.30
     document
    -0.30
    heit
    -0.29
    balleur
    -0.29
    Dap
    -0.29
    lehrer
    -0.29
     impetus
    -0.29
    POSITIVE LOGITS
    BeginContext
    0.80
    AnchorStyles
    0.67
    SequentialGroup
    0.66
     ब्रेकडाउन
    0.66
    httphttps
    0.66
    existsSync
    0.57
     createSprite
    0.57
     Wiktionnaire
    0.57
    aarrggbb
    0.55
    transQ
    0.55
    Activations Density 0.324%

    No Known Activations