© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7076
    Prev
    Next
    INDEX
    Explanations

    references to data structures and processes related to visual scenes and graphs

    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
    Демографія
    -0.44
    ValueStyle
    -0.43
    adpleegd
    -0.39
    CodeAttribute
    -0.38
     Recruit
    -0.38
    ruiter
    -0.37
    estrel
    -0.36
    TextSpan
    -0.35
     OFDb
    -0.35
    tink
    -0.35
    POSITIVE LOGITS
     scene
    1.04
    scene
    0.91
     Scene
    0.90
     camera
    0.90
    Scene
    0.85
     escena
    0.83
    camera
    0.82
     Szene
    0.81
     SCENE
    0.80
     scenes
    0.79
    Activations Density 0.238%

    No Known Activations