© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4839
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "en" in various contexts

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

    Preceding "into"

    np_acts-logits-general · gemini-2.0-flash

    into + article + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ohjel
    -0.61
    intenant
    -0.54
    botten
    -0.54
    脚注の使い方
    -0.54
     vœ
    -0.52
     nôtre
    -0.51
     bénévol
    -0.51
    lijck
    -0.50
     Mexique
    -0.48
     Romains
    -0.48
    POSITIVE LOGITS
     localObject
    0.55
     на
    0.49
    FetchType
    0.49
     به
    0.49
     Be
    0.49
     Patriotic
    0.49
     при
    0.48
     neo
    0.47
     Neo
    0.47
    На
    0.46
    Activations Density 0.352%

    No Known Activations