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. 4821
    Prev
    Next
    INDEX
    Explanations

    elements related to email headers and MIME types in programming contexts

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

    C++ code: newlines and stream insertion operator

    np_acts-logits-general · gemini-2.0-flash

    newline characters in output

    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
    %)$
    -0.71
    IContainer
    -0.63
    %"),
    -0.62
    tagext
    -0.58
    })$}
    -0.58
    IComponent
    -0.57
    cipes
    -0.56
    )$}
    -0.56
    Geplaatst
    -0.54
    )");
    
    -0.53
    POSITIVE LOGITS
     newline
    0.82
     "\
    0.75
     HasFactory
    0.74
    newLine
    0.69
     endl
    0.69
    br
    0.65
    ("\
    0.65
     '\
    0.64
    lines
    0.64
     line
    0.62
    Activations Density 0.274%

    No Known Activations