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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1230
    Prev
    Next
    INDEX
    Explanations

    economic terms related to pricing and market conditions

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

    references to distinctions or variations in competitive contexts

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

    determines measurements and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    帖最后由
    -0.60
     named
    -0.58
     Named
    -0.55
    Longest
    -0.53
     intptr
    -0.52
    engah
    -0.51
     nawr
    -0.51
     Names
    -0.51
    Sized
    -0.51
    Попис
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.72
    SourceChecksum
    0.64
     يتيمه
    0.63
     própri
    0.63
    webElementXpaths
    0.61
    fjspx
    0.57
    OrWhiteSpace
    0.54
    DebuggerNonUser
    0.53
     resourceCulture
    0.49
    omiast
    0.49
    Activations Density 0.593%

    No Known Activations