© 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. 9-GEMMASCOPE-RES-16K
    6. 9946
    Prev
    Next
    INDEX
    Explanations

    structured data and metadata elements, likely in a programming or markup language context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципа
    -0.56
    Rujuakan
    -0.55
     oprot
    -0.54
    WebElementEntity
    -0.52
     arşivlendi
    -0.51
     समीक्षाओं
    -0.48
     ویکی‌پدی
    -0.48
    日閲覧
    -0.48
     laſſen
    -0.47
     ſind
    -0.46
    POSITIVE LOGITS
     AssemblyCompany
    0.63
    __(/*!
    0.57
    MethodManager
    0.54
    gestaltung
    0.45
    ador
    0.44
    dia
    0.43
    ality
    0.43
    tiy
    0.42
    "")
    0.42
    lia
    0.41
    Activations Density 1.424%

    No Known Activations