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. 21-GEMMASCOPE-RES-16K
    6. 740
    Prev
    Next
    INDEX
    Explanations

    elements related to circular geometry and shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.69
     ProtoMessage
    -0.69
    abestanden
    -0.60
     समीक्षक
    -0.60
     esquer
    -0.51
    Stair
    -0.50
     Roskov
    -0.48
    IsContent
    -0.48
    鰭
    -0.47
    hibe
    -0.47
    POSITIVE LOGITS
     circle
    2.04
     circles
    1.85
     Circle
    1.77
     circular
    1.73
    circle
    1.69
    Circle
    1.65
     circumference
    1.61
     CIRCLE
    1.59
     ring
    1.59
     Circles
    1.59
    Activations Density 0.521%

    No Known Activations