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. 21-GEMMASCOPE-RES-16K
    6. 990
    Prev
    Next
    INDEX
    Explanations

    terms related to maize breeding and genetic traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDAE
    -0.46
     salam
    -0.45
     lä
    -0.44
     Pah
    -0.43
     Wör
    -0.43
    ohjel
    -0.43
     Caves
    -0.42
    mousse
    -0.41
    salam
    -0.41
    Saj
    -0.40
    POSITIVE LOGITS
     corn
    1.09
     initComponents
    1.06
     Corn
    1.03
    Corn
    0.97
    corn
    0.94
     maize
    0.94
    ThroughAttribute
    0.93
     grain
    0.90
     maíz
    0.90
     Maize
    0.90
    Activations Density 0.262%

    No Known Activations