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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1073
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Solving single-variable equations

    np_acts-logits-general · gemini-2.0-flash

    solve for variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     useAppContext
    -0.46
     CreateTagHelper
    -0.43
     resourceCulture
    -0.43
    ErrUnexpectedEOF
    -0.42
     kaarangay
    -0.42
    請繼續往下閱讀
    -0.39
     MenuView
    -0.37
    例句
    -0.36
    出版年
    -0.36
     остро
    -0.35
    POSITIVE LOGITS
    SharedDtor
    0.48
     iParam
    0.47
    writerow
    0.43
    thood
    0.41
     Drapeau
    0.40
    dics
    0.40
    Seeder
    0.40
    ghty
    0.39
     murieron
    0.39
     traffico
    0.39
    Activations Density 1.387%

    No Known Activations