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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15107
    Prev
    Next
    INDEX
    Explanations

    references to ratios and proportions in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lepid
    -0.54
     never
    -0.52
     Ста
    -0.51
     concerns
    -0.50
     ع
    -0.49
     LCCN
    -0.49
    atonin
    -0.48
     ند
    -0.47
    clearTimeout
    -0.47
    Bav
    -0.46
    POSITIVE LOGITS
     ratio
    1.92
     Ratio
    1.75
     ratios
    1.72
     RATIO
    1.68
    ratio
    1.66
     proportion
    1.58
    Ratio
    1.52
     Ratios
    1.48
     Proportion
    1.46
    RATIO
    1.41
    Activations Density 0.206%

    No Known Activations