© 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. 18-GEMMASCOPE-RES-16K
    11. 6081
    Prev
    Next
    INDEX
    Explanations

    references to chemical compositions and ratios in scientific contexts

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

    Molar ratios or proportions

    np_acts-logits-general · gemini-2.0-flash

    ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.71
    UnknownFieldSet
    -0.61
     تضيفلها
    -0.55
    enderror
    -0.53
     InputDecoration
    -0.53
     referenties
    -0.52
    गत
    -0.50
    چک
    -0.50
    endous
    -0.50
    ressible
    -0.50
    POSITIVE LOGITS
     ratio
    2.30
     ratios
    2.10
     Ratio
    2.08
    ratio
    1.95
     Ratios
    1.92
     RATIO
    1.90
    Ratio
    1.87
    ratios
    1.70
    RATIO
    1.62
     proportions
    1.55
    Activations Density 0.536%

    No Known Activations