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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4255
    Prev
    Next
    INDEX
    Explanations

    descriptions of plant breeding lines 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
    MigrationBuilder
    -0.74
    HandlerContext
    -0.66
    IsMutable
    -0.66
     Савезне
    -0.65
     Normdatei
    -0.63
    iastes
    -0.63
    SequentialGroup
    -0.62
     Biôgrafia
    -0.59
     <<<<<<<<<<<<<<
    -0.56
     bezeichneter
    -0.55
    POSITIVE LOGITS
     bred
    1.03
     breeding
    0.99
     strain
    0.98
     strains
    0.97
     breed
    0.95
     hybrids
    0.94
     varieties
    0.94
     crosses
    0.92
     hybrid
    0.90
     breeders
    0.90
    Activations Density 0.588%

    No Known Activations