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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5076
    Prev
    Next
    INDEX
    Explanations

    references to beauty products and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     مرئيه
    -0.74
     '\\;'
    -0.73
    saraba
    -0.55
     témoins
    -0.53
    oflavin
    -0.53
    ricians
    -0.53
     Hobson
    -0.52
     pédagog
    -0.51
    Дереккөздер
    -0.49
     plowing
    -0.49
    POSITIVE LOGITS
     fragrance
    1.80
     scent
    1.78
     scents
    1.63
     fragrances
    1.55
     perfume
    1.52
     smells
    1.50
     smell
    1.47
     Scent
    1.44
     Fragrance
    1.44
     smelling
    1.44
    Activations Density 0.070%

    No Known Activations