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. 15474
    Prev
    Next
    INDEX
    Explanations

    code-related functions and methods typically found in programming APIs

    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
    Slf
    -0.90
     createState
    -0.67
    Tē
    -0.65
     Administrativna
    -0.63
    Clik
    -0.59
     informée
    -0.56
    Parcelize
    -0.53
    {~
    -0.49
    Välislingid
    -0.48
    vVar
    -0.48
    POSITIVE LOGITS
    <bos>
    0.62
     betweenstory
    0.62
     McDonough
    0.57
    征詢
    0.53
    appspot
    0.52
    manni
    0.52
    googleapis
    0.49
    Zusammenfassung
    0.49
    esch
    0.49
    Formazione
    0.49
    Activations Density 8.445%

    No Known Activations