© 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. 34-GEMMASCOPE-RES-16K
    11. 5293
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and programming concepts, particularly those involving boxes, charts, and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GIVEREF
    -0.38
    Erreferentziak
    -0.27
    ɵɵelementEnd
    -0.27
     }}(\
    -0.27
     estekak
    -0.27
    something
    -0.27
     propOrder
    -0.27
    цездатний
    -0.26
    WriteBarrier
    -0.26
    jsxFileName
    -0.26
    POSITIVE LOGITS
     ddelwed
    0.73
    ⪜
    0.72
    Дерекк
    0.71
    久しぶ
    0.70
     sesso
    0.69
     metadata
    0.69
     ſans
    0.67
    ロウィン
    0.67
     beſte
    0.66
    оргаш
    0.66
    Activations Density 0.421%

    No Known Activations