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. 9628
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of extension or expansion

    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
     kasarigan
    -0.70
     <=",
    -0.58
    bigsqcup
    -0.58
    ThemeProvider
    -0.57
    ammen
    -0.55
    onyx
    -0.54
    Geplaatst
    -0.53
    logeny
    -0.53
    jspx
    -0.52
     '{@
    -0.52
    POSITIVE LOGITS
     across
    0.70
     extended
    0.67
     extends
    0.66
     expanded
    0.64
     everywhere
    0.62
     reach
    0.61
     extend
    0.61
     även
    0.60
     extending
    0.58
     wider
    0.57
    Activations Density 0.571%

    No Known Activations