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. 5011
    Prev
    Next
    INDEX
    Explanations

    ingredients and dishes related to food preparation and recipes

    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
    atrième
    -0.61
     quelconque
    -0.56
    bör
    -0.55
     chaves
    -0.54
     feroit
    -0.53
    IconModule
    -0.53
    pherals
    -0.53
     proprement
    -0.53
     enfans
    -0.52
     domés
    -0.52
    POSITIVE LOGITS
     صوتيه
    0.55
    Personendaten
    0.52
    principalTable
    0.51
     &
    0.50
    ResponseEntity
    0.49
     infused
    0.49
    addGap
    0.49
     intptr
    0.47
    }{$
    0.47
     JpaRepository
    0.47
    Activations Density 0.088%

    No Known Activations