© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9896
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to scientific equations and parameters

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

    LaTeX math notation, particularly subscripts and superscripts in mathematical formulas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     posesión
    -0.27
     and
    -0.24
    </i>
    -0.24
     Leuten
    -0.24
    </b>
    -0.23
    but
    -0.21
     have
    -0.20
    .
    -0.20
    </strong>
    -0.20
     has
    -0.20
    POSITIVE LOGITS
    хьтан
    0.99
    MLLoader
    0.90
    BibitemShut
    0.86
    ⟬
    0.85
     queſta
    0.85
    باردا
    0.85
    󠁣
    0.85
    Personendaten
    0.84
    нгред
    0.84
     kaarangay
    0.84
    Activations Density 0.843%

    No Known Activations