© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 46256
    Prev
    Next
    INDEX
    Explanations

    indefinite articles ("a" and "an")

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

    phrases starting with "with a" or "with an"

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     plufieurs
    -0.57
     løpet
    -0.50
    出版年
    -0.50
     صوتيه
    -0.48
     pétrole
    -0.47
    RegressionTest
    -0.47
     endblock
    -0.47
    曖昧さ回避
    -0.47
    mergeFrom
    -0.46
    parsedMessage
    -0.46
    POSITIVE LOGITS
    with
    0.82
    With
    0.73
     WITH
    0.71
     with
    0.69
     With
    0.69
    WITH
    0.65
     regard
    0.61
     Avec
    0.61
     emphasis
    0.61
     avec
    0.60
    Activations Density 0.047%

    No Known Activations