© 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. 6093
    Prev
    Next
    INDEX
    Explanations

    cohesive phrases and structures related to visual or thematic elements

    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
    exitRule
    -0.51
    Ārējās
    -0.48
     defaultstate
    -0.45
    󠁢
    -0.40
     مشين
    -0.40
     gambe
    -0.39
     braccia
    -0.38
     <>",
    -0.37
     acque
    -0.37
    sizeCache
    -0.36
    POSITIVE LOGITS
     spot
    3.16
     Spot
    2.92
    spot
    2.86
    Spot
    2.77
     spots
    2.73
     Spots
    2.45
     SPOT
    2.45
    spots
    2.44
    SPOT
    2.30
     dot
    2.28
    Activations Density 0.765%

    No Known Activations