© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2070
    Prev
    Next
    INDEX
    Explanations

    color values and specifications in a graphical or digital context

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

    Color or pixel values (r, g, b, a)

    np_acts-logits-general · gemini-2.0-flash

    color channels and pixel values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    :✨
    -0.37
     surla
    -0.37
    InitStruct
    -0.34
     Shaped
    -0.33
     Shape
    -0.33
    ibatis
    -0.31
    IntoConstraints
    -0.31
    écoute
    -0.30
    Knit
    -0.30
     Curved
    -0.30
    POSITIVE LOGITS
     AssemblyVersion
    0.94
     pigments
    0.60
    aarrggbb
    0.58
     pigment
    0.58
     ffilmiau
    0.54
     pixels
    0.53
     PeEnEo
    0.53
    تفصیلات
    0.51
     Pixels
    0.50
    XmlAccessType
    0.50
    Activations Density 0.193%

    No Known Activations