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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11249
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to lawsuits and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     kasarigan
    -0.67
    таратура
    -0.56
     للمعارف
    -0.54
    IntoConstraints
    -0.54
     coscienza
    -0.52
    transQ
    -0.52
     nakalista
    -0.52
    /***/
    -0.51
    postsleuth
    -0.51
     étoit
    -0.50
    POSITIVE LOGITS
     propOrder
    0.59
    InjectAttribute
    0.49
    fillType
    0.45
    ™
    0.41
     AspNetCore
    0.38
    ®
    0.38
    xnn
    0.36
     bru
    0.35
    省市镇
    0.35
    nextDouble
    0.35
    Activations Density 3.017%

    No Known Activations