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. 12-GEMMASCOPE-RES-16K
    6. 9520
    Prev
    Next
    INDEX
    Explanations

    entities related to positions, roles, or titles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     religieuses
    -0.93
     varandra
    -0.88
     ainfi
    -0.80
    Obrázky
    -0.73
     ulei
    -0.72
     aveug
    -0.71
     adaptées
    -0.71
     auxquelles
    -0.71
     avoient
    -0.71
     suivantes
    -0.70
    POSITIVE LOGITS
     own
    0.91
     my
    0.83
     final
    0.81
     its
    0.80
    ின்
    0.76
     recent
    0.73
     ultimate
    0.72
    ++){
    
    0.72
     latest
    0.71
     main
    0.70
    Activations Density 0.110%

    No Known Activations