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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 7489
    Prev
    Next
    INDEX
    Explanations

    terms related to specific geological and environmental concepts and measurements

    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
    ölkerung
    -0.53
    AddTagHelper
    -0.52
     AssemblyCulture
    -0.50
    tvguidetime
    -0.50
    Rüyada
    -0.48
    Closed
    -0.47
     Closed
    -0.45
     chio
    -0.44
    getMenuInflater
    -0.44
    BrowserModule
    -0.43
    POSITIVE LOGITS
     extends
    1.88
     extend
    1.81
     extending
    1.72
     spans
    1.58
    extend
    1.54
     Extend
    1.50
    extends
    1.49
     Extending
    1.47
     extended
    1.46
     spanning
    1.38
    Activations Density 0.606%

    No Known Activations