© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8931
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistical measurements regarding probability and odds within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.64
    transQ
    -0.60
    makeConstraints
    -0.59
    RenderAtEndOf
    -0.57
     Administrativna
    -0.57
     CURIAM
    -0.57
    ValueStyle
    -0.57
     protoimpl
    -0.55
    UrlResolution
    -0.55
     صوتيه
    -0.55
    POSITIVE LOGITS
    Бахар
    0.41
    iNdEx
    0.39
    live
    0.36
     watch
    0.36
     change
    0.32
     maintained
    0.32
     Watch
    0.32
    нача
    0.31
    initialState
    0.31
    Watch
    0.31
    Activations Density 1.716%

    No Known Activations