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. 9-GEMMASCOPE-RES-16K
    6. 3548
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to magnetic interactions in materials, particularly those involving Heisenberg exchange

    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
     vru
    -0.40
     pedagang
    -0.38
    flickr
    -0.38
    baguna
    -0.38
     दर
    -0.37
    fatalError
    -0.37
    getColumnIndex
    -0.36
     Wiseman
    -0.35
     sı
    -0.34
    δη
    -0.33
    POSITIVE LOGITS
     PeEnEo
    0.66
    RefNanny
    0.56
    InjectAttribute
    0.56
    出版年
    0.55
    ValueStyle
    0.54
     informée
    0.52
     snippetHide
    0.51
    KommentareTeilen
    0.51
    رشف
    0.50
     '\\;'
    0.50
    Activations Density 1.036%

    No Known Activations