© 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. 53897
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries about processes and comparisons

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

    mathematical notation and German words

    np_acts-logits-general · gemini-2.5-flash-lite

    the first real word following the start-of-sequence marker (i.e., sentence/document openings).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     et
    -0.30
    які
    -0.26
     يتيمه
    -0.26
     ब्रेकडाउन
    -0.25
     etc
    -0.24
     Figure
    -0.24
     Users
    -0.23
    因
    -0.23
    _
    -0.23
    特定
    -0.22
    POSITIVE LOGITS
    niſſe
    0.82
    iſen
    0.82
    iſchen
    0.82
    ſicht
    0.81
    iſten
    0.81
     beſte
    0.80
    ſſung
    0.79
     queſta
    0.79
     Infór
    0.79
    ðsíða
    0.78
    Activations Density 0.643%

    No Known Activations