Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4672
    Prev
    Next
    INDEX
    Explanations

    terms related to shades of gray and their representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amiens
    -0.82
     Donnie
    -0.80
    ngdoc
    -0.78
     magnétique
    -0.75
     vivement
    -0.74
     propOrder
    -0.74
    &&&
    -0.74
    JCheckBox
    -0.72
     tarko
    -0.72
     Hooper
    -0.72
    POSITIVE LOGITS
     Gray
    1.37
    GRAY
    1.28
     Grey
    1.28
     GRAY
    1.26
    Gray
    1.22
     gray
    1.19
     GREY
    1.15
    gray
    1.11
    Grey
    1.09
    GREY
    1.09
    Activations Density 0.154%

    No Known Activations