© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11045
    Prev
    Next
    INDEX
    Explanations

    phrases that express percentages and ratios in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.89
     resourceCulture
    -0.71
     Wikispecies
    -0.71
     gynhyrchwyd
    -0.69
     Kays
    -0.68
    يكب
    -0.67
    FieldBuilder
    -0.66
     kasarigan
    -0.65
    dbury
    -0.65
    PhysRevD
    -0.65
    POSITIVE LOGITS
     percentage
    1.20
     (%)
    1.09
    percentage
    1.04
     percent
    1.03
     percentages
    1.02
     Percentage
    0.99
    Percentage
    0.94
     pourcentage
    0.94
     %
    0.94
     PERCENT
    0.93
    Activations Density 0.364%

    No Known Activations