© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    numerical data and mathematical operations

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

    Mathematical/scientific negative values

    np_acts-logits-general · gemini-2.0-flash

    mathematical intervals and negative numbers

    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
     Appel
    -0.44
     wh
    -0.44
    pl
    -0.42
     شنا
    -0.41
     plural
    -0.41
     magn
    -0.41
    ladas
    -0.40
     kommen
    -0.40
    Mag
    -0.39
    wh
    -0.39
    POSITIVE LOGITS
     (-
    1.17
    (-
    1.16
     negative
    1.11
     [-
    1.04
     negatif
    1.00
     $(-
    1.00
     $-
    0.99
     (−
    0.99
    Negative
    0.95
    negative
    0.94
    Activations Density 0.938%

    No Known Activations