© 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. 4729
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to software or hardware systems

    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
     autorytatywna
    -0.81
    ThroughAttribute
    -0.78
    ロウィン
    -0.68
     فريبيس
    -0.66
     imagui
    -0.64
     utafitiHapana
    -0.63
    ﹧
    -0.63
     protoimpl
    -0.63
     tartalo
    -0.62
    adpleegd
    -0.61
    POSITIVE LOGITS
    MemoryWarning
    0.33
    osť
    0.30
     image
    0.29
     문
    0.28
     sympathique
    0.28
     english
    0.27
    gabung
    0.26
     clicking
    0.26
     culture
    0.26
     hàng
    0.26
    Activations Density 1.545%

    No Known Activations