© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5997
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

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

    Mathematical problem introductions

    np_acts-logits-general · gemini-2.0-flash

    mathematical problem explanation

    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
     talvez
    -0.54
    formik
    -0.53
    istoitu
    -0.50
    setVerticalGroup
    -0.47
     maybe
    -0.46
    Esperamos
    -0.43
    Прият
    -0.43
     cref
    -0.43
    Akhir
    -0.42
     Qualquer
    -0.42
    POSITIVE LOGITS
     explain
    1.20
     Explain
    1.15
     describe
    1.14
     Describe
    1.10
     what
    1.07
    Explain
    1.06
    Describe
    1.04
     What
    1.02
    explain
    0.99
    Discuss
    0.97
    Activations Density 1.806%

    No Known Activations