© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15790
    Prev
    Next
    INDEX
    Explanations

    references to video and related media content

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

    "video" followed by different media types

    np_acts-logits-general · gemini-2.0-flash

    video games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.76
    })();
    -0.70
    WriteAttribute
    -0.69
     InputDecoration
    -0.65
    |]
    -0.62
     typelib
    -0.61
    elemField
    -0.60
    ритори
    -0.60
     GeoNames
    -0.59
     defaultstate
    -0.58
    POSITIVE LOGITS
    tape
    0.81
     clip
    0.80
     footage
    0.78
     clips
    0.76
     video
    0.75
     videos
    0.71
    Video
    0.71
     Video
    0.70
    video
    0.70
    VIDEO
    0.68
    Activations Density 0.135%

    No Known Activations