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. 13661
    Prev
    Next
    INDEX
    Explanations

    references to specific gaming mechanics or abilities

    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
     angina
    -0.53
     socialista
    -0.52
     саны
    -0.47
    stool
    -0.46
    blau
    -0.46
    dealloc
    -0.44
    aconda
    -0.44
    RTHOOK
    -0.43
    :✨
    -0.42
    cuba
    -0.42
    POSITIVE LOGITS
     Dota
    0.76
     League
    0.73
     LoL
    0.71
    レーン
    0.67
    Dota
    0.64
     esports
    0.63
     Esports
    0.62
    IntoConstraints
    0.62
    League
    0.61
     eSports
    0.61
    Activations Density 0.052%

    No Known Activations