© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 8703
    Prev
    Next
    INDEX
    Explanations

    color-related terms and formatting styles in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colors
    -1.18
     Colors
    -1.11
     color
    -1.10
    colors
    -1.06
    Color
    -1.04
     Color
    -1.03
    Colors
    -1.02
     colours
    -1.00
     Colours
    -0.97
    color
    -0.96
    POSITIVE LOGITS
    EnableWeb
    0.63
    exels
    0.60
     AssemblyTitle
    0.59
     téléchargez
    0.57
    hound
    0.56
    точници
    0.55
     transfieras
    0.54
    ">—
    0.54
     AssemblyCompany
    0.53
     signé
    0.53
    Activations Density 0.169%

    No Known Activations