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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13469
    Prev
    Next
    INDEX
    Explanations

    pronouns and their associated verbs indicating potential actions or commitments

    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
     Meksiku
    -0.62
     disambiguazione
    -0.60
    EndInit
    -0.59
     pinulongan
    -0.54
    Rüyada
    -0.54
     noDo
    -0.54
    GEBURTSDATUM
    -0.53
    twimg
    -0.52
    jspb
    -0.50
    etheless
    -0.50
    POSITIVE LOGITS
     can
    0.76
     puissiez
    0.75
     hopefully
    0.70
     möglichst
    0.68
     بتوان
    0.64
    hopefully
    0.63
     possano
    0.61
    就不会
    0.61
    就可以
    0.61
     possa
    0.60
    Activations Density 0.185%

    No Known Activations