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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5099
    Prev
    Next
    INDEX
    Explanations

    instances of dates and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     CreateTagHelper
    -0.79
    SHADER
    -0.51
    URIComponent
    -0.50
    嘩
    -0.50
    плу
    -0.48
    oregon
    -0.47
     nas
    -0.47
    Tbh
    -0.47
     Achtung
    -0.46
    GMENT
    -0.46
    POSITIVE LOGITS
    indd
    0.61
    Diweddarwch
    0.61
    govina
    0.59
    TypedDataSet
    0.58
     disambiguazione
    0.58
    FieldBuilder
    0.57
    subsubsection
    0.55
    . 
    0.55
     acestui
    0.55
     فريبيس
    0.53
    Activations Density 0.135%

    No Known Activations