© 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. 41-GEMMASCOPE-RES-16K
    11. 9998
    Prev
    Next
    INDEX
    Explanations

    actions and interactions related to doors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    énario
    -0.45
    basicConfig
    -0.39
    atimes
    -0.36
    帖最后由
    -0.36
    Trichloroethane
    -0.36
    ᅠ
    -0.35
    ForResult
    -0.34
     poursuivre
    -0.34
    CodeAnalysis
    -0.33
    FirstResponder
    -0.33
    POSITIVE LOGITS
     door
    3.05
     doors
    2.55
     Door
    2.47
    Door
    2.42
    door
    2.39
     DOOR
    2.36
     puerta
    2.17
     Doors
    2.09
     doorway
    2.06
    doors
    2.05
    Activations Density 0.388%

    No Known Activations