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. 22-GEMMASCOPE-RES-16K
    6. 14099
    Prev
    Next
    INDEX
    Explanations

    descriptions and evaluations of media, particularly regarding diversity and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.82
    ]<<"
    -0.70
     فريبيس
    -0.69
    enderror
    -0.68
    出版年
    -0.67
     betweenstory
    -0.67
    aarrggbb
    -0.66
    parsedMessage
    -0.65
    offsetof
    -0.64
     whofe
    -0.63
    POSITIVE LOGITS
     appunto
    0.64
     ironically
    0.61
     among
    0.61
     again
    0.57
     näin
    0.56
     in
    0.55
    Попис
    0.55
     unfortunately
    0.54
     importantly
    0.53
     understandably
    0.53
    Activations Density 0.215%

    No Known Activations