© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 388
    Prev
    Next
    INDEX
    Explanations

    references to filmmaking and camera equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to filmmaking and video production processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    camera, video, number, quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.67
    InputBorder
    -0.63
     ujednoznacz
    -0.58
    awtextra
    -0.58
     سكانية
    -0.55
     समीक्षाओं
    -0.53
    IsContent
    -0.52
     Parton
    -0.52
     Obrador
    -0.50
    csol
    -0.49
    POSITIVE LOGITS
     camera
    1.73
     cameras
    1.65
     Cameras
    1.41
     camer
    1.41
    camera
    1.40
     Camera
    1.39
    Camera
    1.33
    cameras
    1.32
     filming
    1.29
     kamera
    1.26
    Activations Density 0.096%

    No Known Activations