© 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. 14683
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to mathematical calculations, particularly those involving greatest common factors and divisors

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

    "Greatest," "highest," "max," or "biggest"

    np_acts-logits-general · gemini-2.0-flash

    greatest common factor or divisor

    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
    parsedMessage
    -0.55
    VersionUID
    -0.48
    FieldOffsetTable
    -0.48
     ſche
    -0.47
    psfrag
    -0.46
     ویکی‌پدیای
    -0.46
    RenderAtEndOf
    -0.46
    Gön
    -0.45
     IBOutlet
    -0.45
     poff
    -0.45
    POSITIVE LOGITS
     brightest
    0.46
    max
    0.46
     max
    0.45
     BEST
    0.44
    best
    0.44
     best
    0.44
     maksimal
    0.44
     maksimum
    0.43
     among
    0.41
    est
    0.40
    Activations Density 0.679%

    No Known Activations