© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14594
    Prev
    Next
    INDEX
    Explanations

    elements related to crafting and making things with materials

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

    Crude, basic, or do-it-yourself objects

    np_acts-logits-general · gemini-2.0-flash

    homemade and improvised items

    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
     táctil
    -0.43
     poivre
    -0.38
     bordada
    -0.36
    deutig
    -0.36
     Einfluß
    -0.34
     décret
    -0.34
    ModelSerializer
    -0.33
     acier
    -0.33
     inoxidable
    -0.33
     templado
    -0.33
    POSITIVE LOGITS
     homemade
    0.74
     improvised
    0.72
     DIY
    0.71
     Homemade
    0.71
    DIY
    0.70
     makeshift
    0.69
    Homemade
    0.66
    homemade
    0.65
    IsMutable
    0.63
     Wikimedijinoj
    0.58
    Activations Density 0.286%

    No Known Activations