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. 2233
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those associated with entertainment or celebrity culture

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

    followed by suffixes (-man, -ren, -sen, etc.)

    np_acts-logits-general · gemini-2.0-flash

    surnames of people

    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
     
    -0.56
     et
    -0.51
    ,
    -0.49
     a
    -0.48
    ↵↵
    -0.47
     um
    -0.47
     the
    -0.46
     all
    -0.46
    .
    -0.46
     consistent
    -0.45
    POSITIVE LOGITS
    abetes
    0.94
    
    0.94
     Administrativna
    0.89
    mybatisplus
    0.89
    IGraphics
    0.87
     onAnimation
    0.87
    +:+
    0.86
     Anſ
    0.86
     Efq
    0.86
    +#+#
    0.85
    Activations Density 0.219%

    No Known Activations