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. 16-GEMMASCOPE-RES-16K
    6. 15785
    Prev
    Next
    INDEX
    Explanations

    scientific studies related to medical conditions and their treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a colon

    np_acts-logits-general · gemini-2.0-flash

    scientific findings and case reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.78
     Efq
    -0.78
    expandindo
    -0.73
     Monfieur
    -0.71
    Carriera
    -0.70
     Shakspeare
    -0.69
     Majefty
    -0.69
    principalColumn
    -0.68
     resourceCulture
    -0.67
    tonode
    -0.65
    POSITIVE LOGITS
     case
    0.57
     what
    0.56
     worth
    0.55
    허
    0.54
     report
    0.51
     Part
    0.50
     pros
    0.50
     ¿
    0.50
     possible
    0.49
    <!--[
    0.49
    Activations Density 0.129%

    No Known Activations