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. 9637
    Prev
    Next
    INDEX
    Explanations

    references to specific events or organizations related to community activities

    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
    :][
    -0.65
    bootstrapcdn
    -0.65
     Bunga
    -0.57
    WebVitals
    -0.56
     يتيمه
    -0.55
    川崎
    -0.54
    KHR
    -0.53
     Khart
    -0.53
    iczny
    -0.53
    imakasih
    -0.53
    POSITIVE LOGITS
     Irish
    1.52
    Irish
    1.36
     Dublin
    1.35
     Ireland
    1.34
    Ireland
    1.25
    Dublin
    1.19
     irish
    1.14
     Limerick
    1.08
     Galway
    1.06
     IRELAND
    1.06
    Activations Density 0.224%

    No Known Activations