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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 2795
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly in a formatted way

    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
    
    -0.74
    новништво
    -0.56
     of
    -0.52
    …
    -0.52
     to
    -0.52
    dotenv
    -0.51
     â
    -0.49
     @
    -0.48
     https
    -0.48
     in
    -0.48
    POSITIVE LOGITS
     }}$}
    0.72
     RIPRODUZIONE
    0.69
    thâu
    0.68
     Kombat
    0.68
     Shakspeare
    0.67
    })*/
    0.66
     niedersachsen
    0.66
    soever
    0.65
    NUMX
    0.65
    middels
    0.64
    Activations Density 1.048%

    No Known Activations