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. 6460
    Prev
    Next
    INDEX
    Explanations

    terms related to fishing equipment

    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
    URIComponent
    -0.57
     administrativos
    -0.56
     administrativo
    -0.55
     تضيفلها
    -0.51
    LAV
    -0.51
     محفوظة
    -0.50
    ollectionView
    -0.49
     lccn
    -0.49
     للاسماء
    -0.48
    esModule
    -0.47
    POSITIVE LOGITS
     fishing
    1.68
     fished
    1.47
     Fishing
    1.47
    Fishing
    1.44
    fishing
    1.41
     anglers
    1.40
     angler
    1.37
     fisherman
    1.30
     fish
    1.29
     fishermen
    1.29
    Activations Density 0.084%

    No Known Activations