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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5995
    Prev
    Next
    INDEX
    Explanations

    words related to co-authorship and collaboration in projects

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

    Appearing before titles or roles

    np_acts-logits-general · gemini-2.0-flash

    co-founder, co-author, co-director

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Afrique
    -0.61
     Intervention
    -0.60
    TagHelper
    -0.60
     resulta
    -0.59
    WriteLiteral
    -0.58
    servername
    -0.58
     Barbier
    -0.57
     remplace
    -0.57
    ങ്ങ
    -0.57
    plor
    -0.57
    POSITIVE LOGITS
     coö
    0.62
    TintMode
    0.61
     Şi
    0.60
     Osh
    0.59
     alms
    0.58
     photolibrary
    0.57
     Rha
    0.57
     rafting
    0.56
     blest
    0.56
     parch
    0.55
    Activations Density 0.219%

    No Known Activations