© 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. 36-GEMMASCOPE-RES-16K
    11. 12971
    Prev
    Next
    INDEX
    Explanations

    statements related to actions involving movement or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ندران
    -0.32
    ppsala
    -0.29
    ortheast
    -0.28
    觉
    -0.28
    ívne
    -0.28
    tanooga
    -0.28
    ‸
    -0.28
    πισ
    -0.27
     místě
    -0.27
     собой
    -0.27
    POSITIVE LOGITS
     through
    3.42
    through
    2.97
     Through
    2.89
    Through
    2.89
     THROUGH
    2.72
    THROUGH
    2.44
     attraverso
    2.28
     thru
    2.23
     через
    2.17
     melalui
    2.16
    Activations Density 1.448%

    No Known Activations