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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3415
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and terms related to formal definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.60
    parsedMessage
    -0.52
    сылкі
    -0.50
    ագրություններ
    -0.49
    Източници
    -0.49
     autorytatywna
    -0.48
     للمعارف
    -0.47
    存于互联网档案馆
    -0.47
    SharedDtor
    -0.47
     Grüsse
    -0.46
    POSITIVE LOGITS
    createStatement
    0.47
     absolute
    0.46
    absolute
    0.46
    oforte
    0.45
    RectangleBorder
    0.44
     partial
    0.43
     мәкал
    0.42
     private
    0.41
     whole
    0.41
     choice
    0.40
    Activations Density 0.491%

    No Known Activations