Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6773
    Prev
    Next
    INDEX
    Explanations

    references to companies and their associated products or services

    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
    myModal
    -0.61
    <unused63>
    -0.54
     túl
    -0.51
    etragen
    -0.47
     darbu
    -0.46
    jelent
    -0.45
     newBuilder
    -0.45
    ūd
    -0.45
     competencias
    -0.44
     vermelhas
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.94
    ագրություններ
    0.92
    FunctionFlags
    0.80
     NSCoder
    0.78
    ConstraintMaker
    0.77
    IntoConstraints
    0.74
     Linkedin
    0.73
    AutoScaleMode
    0.73
    EndContext
    0.71
    itinéraire
    0.71
    Activations Density 0.487%

    No Known Activations