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. 20-GEMMASCOPE-RES-16K
    6. 9353
    Prev
    Next
    INDEX
    Explanations

    names, particularly those associated with the term "Kai" and its variants

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

    or names starting with "Kai", "Mai", "Sai", or "Ai"

    np_acts-logits-general · gemini-2.0-flash

    names and initials

    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-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
     meantime
    -1.36
     meanwhile
    -1.26
    Meanwhile
    -1.22
     Meanwhile
    -1.22
    mean
    -0.98
     frattempo
    -0.94
     mean
    -0.93
    Mean
    -0.91
     Sementara
    -0.89
     Mean
    -0.89
    POSITIVE LOGITS
    ̯
    1.14
    Kjelder
    0.68
    webElementXpaths
    0.65
    sizeCache
    0.64
     griega
    0.63
     صوتيه
    0.63
     Solidity
    0.61
    borderSide
    0.61
     antiquity
    0.59
    jury
    0.56
    Activations Density 0.118%

    No Known Activations