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

    Neuronpedia

    Jacobian LensNEW
    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. 15348
    Prev
    Next
    INDEX
    Explanations

    references to letters, especially when associated with grading or classifications

    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
    extField
    -0.46
     Houſe
    -0.46
    aneity
    -0.45
     Efq
    -0.45
     Inſ
    -0.45
     Reſ
    -0.45
     tapete
    -0.45
     Perſ
    -0.44
    afficheront
    -0.44
     faſt
    -0.44
    POSITIVE LOGITS
    fromCharCode
    0.82
     letter
    0.79
     letters
    0.75
    Letter
    0.71
     Letter
    0.67
     Letters
    0.67
     LETTER
    0.66
    letter
    0.65
    Letters
    0.65
    letters
    0.63
    Activations Density 1.070%

    No Known Activations