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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 802
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to quantities and their relationships in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EFIAPI
    -0.58
    principalColumn
    -0.54
    EndProject
    -0.53
     فريبيس
    -0.50
    出版年
    -0.49
     okuyayım
    -0.48
    ########.
    -0.47
     wię
    -0.44
     tričko
    -0.44
     surla
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.57
    ****/
    0.38
    endpush
    0.35
    ../
    0.35
    énier
    0.34
     Containers
    0.34
    *****/
    0.34
    法人
    0.34
    ://
    0.34
    umbledore
    0.33
    Activations Density 0.037%

    No Known Activations