Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9926
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting commands in LaTeX documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    เภ
    -0.57
    {{/
    -0.56
    VIAF
    -0.54
    IsPostBack
    -0.54
     createSprite
    -0.51
    Сылтамалар
    -0.50
    '},
    
    -0.49
    awić
    -0.48
     Arkivert
    -0.47
    ┬
    -0.46
    POSITIVE LOGITS
    \
    0.83
    DeleteBehavior
    0.76
     \
    0.67
     $\
    0.66
    
    0.65
     kaynağından
    0.64
     <<<<<<<<<<<<<<
    0.63
     defStyleAttr
    0.61
    MessageTagHelper
    0.58
    DoubleQuotes
    0.58
    Activations Density 0.181%

    No Known Activations