© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3449
    Prev
    Next
    INDEX
    Explanations

    references to colors and coloring materials in art-related contexts

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

    mentions of specific coloring supplies and art materials, particularly Copic markers and colored pencils.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.50
    AddTagHelper
    -0.44
     <<<<<<<<<<<<<<
    -0.43
    InvalidProtocol
    -0.42
     Nieren
    -0.42
     minOccurs
    -0.41
    RenderAtEndOf
    -0.41
    MLLoader
    -0.39
    simpleType
    -0.39
     nahilalakip
    -0.39
    POSITIVE LOGITS
     pen
    1.49
     pencil
    1.46
     pens
    1.41
     pencils
    1.38
     Pencil
    1.23
     Pen
    1.20
    pencil
    1.17
    Pencil
    1.17
    Pen
    1.16
     Pens
    1.14
    Activations Density 0.114%

    No Known Activations