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. 9611
    Prev
    Next
    INDEX
    Explanations

    the presence of technical terms related to analytical processes and measurements in various contexts

    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
     agriculture
    -0.73
     football
    -0.70
     sports
    -0.69
     fotbal
    -0.68
     soccer
    -0.67
     agricultural
    -0.66
     basketball
    -0.64
     baseball
    -0.63
     fotball
    -0.62
     bpy
    -0.62
    POSITIVE LOGITS
     kasarigan
    0.71
    :✨
    0.61
    rungsseite
    0.61
    IntoConstraints
    0.59
    AsUp
    0.58
     lượt
    0.57
    ✭✭
    0.56
    ьа
    0.56
    ู่
    0.55
    enderror
    0.55
    Activations Density 0.785%

    No Known Activations