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. 20-GEMMASCOPE-RES-16K
    6. 6493
    Prev
    Next
    INDEX
    Explanations

    references to medical and scientific organizations and their activities

    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
    Geplaatst
    -0.85
     بيها
    -0.80
     AssemblyCulture
    -0.77
    IndentedString
    -0.76
    Personendaten
    -0.72
    GEBURTSDATUM
    -0.71
     محفوظة
    -0.71
    principalColumn
    -0.67
    numerusform
    -0.65
    DeleteBehavior
    -0.64
    POSITIVE LOGITS
    RTDA
    0.50
    :+:
    0.44
     oprot
    0.42
    arikat
    0.42
     نے
    0.42
    autorest
    0.41
    примеча
    0.40
    NonQuery
    0.40
     employers
    0.40
    ிறது
    0.40
    Activations Density 0.529%

    No Known Activations