© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3771
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogue indicators in text

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

    Quoted speech or dialogue

    np_acts-logits-general · gemini-2.0-flash

    opening quotation mark followed by text

    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
    OGND
    -0.80
     ExecuteAsync
    -0.76
    rungsseite
    -0.75
     Италијани
    -0.73
    bootstrapcdn
    -0.72
     ब्रेकडाउन
    -0.71
    iſchen
    -0.70
    [@BOS@]
    -0.70
    <unused8>
    -0.69
    <unused41>
    -0.69
    POSITIVE LOGITS
    “
    0.32
    They
    0.28
    We
    0.28
    śla
    0.26
    થી
    0.25
     faudrait
    0.25
    Then
    0.24
     الو
    0.24
    Someone
    0.24
    entraî
    0.24
    Activations Density 0.073%

    No Known Activations