© 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. 12-GEMMASCOPE-RES-16K
    11. 3492
    Prev
    Next
    INDEX
    Explanations

    references to Common Weakness Enumeration (CWE) identifiers related to software vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benefit
    -0.31
     balance
    -0.30
     passing
    -0.29
    Ausgabe
    -0.29
    Плюсы
    -0.28
    Sommaire
    -0.27
    <tfoot>
    -0.27
     معمول
    -0.27
     balancing
    -0.26
     pass
    -0.26
    POSITIVE LOGITS
    :✨
    9.75
     EconPapers
    1.49
    ✨:
    1.32
     autorytatywna
    1.27
     surla
    1.20
    msgTypes
    1.13
    GEBURTSDATUM
    1.12
     kasarigan
    1.10
    Rüyada
    1.08
     يتيمه
    1.07
    Activations Density 0.055%

    No Known Activations