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. 9849
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to material properties and treatments

    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
     Orrell
    -0.48
    kapnya
    -0.47
     oublié
    -0.47
     quên
    -0.47
    clusão
    -0.46
    Zeneca
    -0.46
     ArrayAdapter
    -0.45
    дыду
    -0.45
     orina
    -0.45
     méri
    -0.45
    POSITIVE LOGITS
     cutting
    1.21
     cut
    1.19
     Cutting
    1.12
    cutting
    1.07
    Cutting
    1.07
     slicing
    1.07
     Cut
    1.04
     cuts
    1.04
     cutter
    1.03
     CUT
    1.03
    Activations Density 0.411%

    No Known Activations