© 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 EvalsExportsinterp-engineNEWAPI 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. 9203
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and references related to people, organizations, and places

    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
     bezeichneter
    -0.55
    Rüyada
    -0.40
    invokeLater
    -0.38
    webElementXpaths
    -0.38
    Ceci
    -0.37
    /**
    -0.37
     Infórmanos
    -0.35
    Modern
    -0.34
    hier
    -0.34
    AutoScaleMode
    -0.34
    POSITIVE LOGITS
    bibfield
    0.50
    extAlignment
    0.44
    getContentPane
    0.44
    andExpect
    0.44
    NewLabel
    0.43
     Pamp
    0.42
     незавершена
    0.42
    点此举报
    0.40
    makeConstraints
    0.40
    onacci
    0.39
    Activations Density 0.288%

    No Known Activations