© 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. 12-GEMMASCOPE-RES-16K
    11. 3995
    Prev
    Next
    INDEX
    Explanations

    programming functions related to graphical or visual rendering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.61
    </tfoot>
    -0.57
     kaarangay
    -0.54
    ConstraintMaker
    -0.54
    setVerticalGroup
    -0.52
    tvguidetime
    -0.50
     protoimpl
    -0.48
    Chham
    -0.48
     certify
    -0.48
    Referensi
    -0.48
    POSITIVE LOGITS
     Mascul
    0.54
    gridx
    0.53
     getWidth
    0.53
     masculine
    0.50
    pageX
    0.49
     mascul
    0.49
    getWidth
    0.48
    SequentialGroup
    0.48
     manly
    0.48
     width
    0.47
    Activations Density 0.334%

    No Known Activations