© 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. 31-GEMMASCOPE-RES-16K
    11. 9766
    Prev
    Next
    INDEX
    Explanations

    elements and operations related to JSON serialization and SQL database interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    assignment operators and equals signs in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dark
    -0.32
     secret
    -0.29
    Ӕ
    -0.28
    BeginContext
    -0.27
     chip
    -0.27
     cal
    -0.27
     consig
    -0.27
     Christian
    -0.27
    Cambio
    -0.26
    FixedSize
    -0.26
    POSITIVE LOGITS
    HtmlAttribute
    0.69
    RenderAtEndOf
    0.68
    BagConstraints
    0.66
    存于互联网档案馆
    0.64
     queſta
    0.62
    ſehen
    0.61
    ValueStyle
    0.60
    FunctionFlags
    0.60
    GraphicsUnit
    0.60
    PreferredItem
    0.60
    Activations Density 0.355%

    No Known Activations