© 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. 20-GEMMASCOPE-RES-16K
    11. 16161
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data related to dismissals and run counts in cricket matches

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

    Negative numbers or subtraction

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Toponymie
    -0.60
     pinulongan
    -0.55
     يتيمه
    -0.54
    tvguidetime
    -0.53
    ormous
    -0.52
     hö
    -0.51
     defStyleAttr
    -0.51
    UserScript
    -0.51
     arşivlendi
    -0.50
    JspWriter
    -0.50
    POSITIVE LOGITS
    Low
    0.55
     poucos
    0.54
     Low
    0.54
     low
    0.54
     LOW
    0.52
     pocos
    0.52
    GeoNames
    0.51
     zero
    0.51
    afficheront
    0.50
     mineures
    0.49
    Activations Density 0.878%

    No Known Activations