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. 4586
    Prev
    Next
    INDEX
    Explanations

    words related to penalties, prison, or incarceration

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

    "Pen" followed by other letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with pen

    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
     nahilalakip
    -0.87
     للمعارف
    -0.86
    }{*}{}
    -0.79
     AssemblyCulture
    -0.73
    (!__
    -0.73
    TagMode
    -0.71
    
    -0.69
     estekak
    -0.68
    \{\\
    -0.68
     صوتيه
    -0.67
    POSITIVE LOGITS
     pen
    0.73
    pen
    0.73
     PEN
    0.68
     Pen
    0.68
     Pens
    0.65
    Pens
    0.63
    Pen
    0.63
     pens
    0.62
     Pena
    0.62
     PENS
    0.61
    Activations Density 0.067%

    No Known Activations