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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2791
    Prev
    Next
    INDEX
    Explanations

    numerical data and mathematical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fifth
    -0.79
     FIVE
    -0.74
    ########.
    -0.71
     fün
    -0.71
     SIX
    -0.70
     Five
    -0.69
     five
    -0.69
     pią
    -0.68
    FIVE
    -0.67
     FIFTH
    -0.67
    POSITIVE LOGITS
     Tenth
    0.59
    9
    0.57
     Ninth
    0.57
     nine
    0.56
    NewUrlParser
    0.55
     Nine
    0.52
     Monday
    0.51
     ninth
    0.51
     समीक्षक
    0.48
    MessageTagHelper
    0.48
    Activations Density 0.441%

    No Known Activations