© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12406
    Prev
    Next
    INDEX
    Explanations

    references to mathematical notation and discussions within sections of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    المناصب
    -0.82
    expandindo
    -0.81
     الحره
    -0.81
    parsedMessage
    -0.80
     estekak
    -0.79
     ویکی‌پدی
    -0.78
     ſind
    -0.75
    ArrowToggle
    -0.73
     tartalomajánló
    -0.73
     كومونز
    -0.72
    POSITIVE LOGITS
     yoksa
    0.44
     muchacha
    0.42
     espoir
    0.38
     Europeo
    0.36
     informativo
    0.36
    enfance
    0.35
     actualidad
    0.35
     coupable
    0.34
     metropolitana
    0.34
     íntimo
    0.34
    Activations Density 0.836%

    No Known Activations