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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12820
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and relationships in equations

    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
     weighted
    -1.04
    weapon
    -1.01
     weapon
    -0.98
     wings
    -0.97
     warning
    -0.97
     weights
    -0.96
     weddings
    -0.96
    warning
    -0.96
     width
    -0.95
     weapons
    -0.95
    POSITIVE LOGITS
    Kaieteur
    0.52
    Portale
    0.51
     postIndex
    0.48
    addCriterion
    0.47
    crata
    0.41
     Союза
    0.41
    ografija
    0.40
    partimento
    0.40
     CRUZ
    0.40
    gione
    0.40
    Activations Density 0.236%

    No Known Activations