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. 21-GEMMASCOPE-RES-16K
    6. 7458
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "figure" and its variations or contexts related to graphical or numerical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellites
    -0.59
     virtuel
    -0.59
     sortBy
    -0.57
     CiNii
    -0.56
     Surreal
    -0.54
    osoba
    -0.54
    ьаж
    -0.53
    beams
    -0.52
     virtuales
    -0.52
    abetes
    -0.51
    POSITIVE LOGITS
     Figures
    1.21
     Figure
    1.19
     figures
    1.10
    Figures
    1.10
     figure
    1.09
    Figure
    0.99
     FIGURE
    0.97
     FIGURES
    0.95
     fig
    0.91
     Figue
    0.87
    Activations Density 0.156%

    No Known Activations