© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11466
    Prev
    Next
    INDEX
    Explanations

    references to leather and related materials

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

    material and fabric descriptions, particularly leather and synthetic textile properties.

    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
    Viitteet
    -0.43
     nonatomic
    -0.41
     supermercado
    -0.41
     opérés
    -0.41
     yyb
    -0.41
     playera
    -0.40
     pijama
    -0.38
    矶
    -0.38
    typeorm
    -0.38
     cuillère
    -0.37
    POSITIVE LOGITS
     leather
    1.55
     Leather
    1.38
    Leather
    1.35
    leather
    1.35
     cuero
    1.16
     چرم
    1.07
     couro
    1.06
     cuir
    0.95
    レザー
    0.90
     tanned
    0.89
    Activations Density 0.086%

    No Known Activations