© 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. 28-GEMMASCOPE-RES-16K
    11. 4197
    Prev
    Next
    INDEX
    Explanations

    tokens that indicate dialogue or quotations

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

    Text within parentheses or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    citations and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    capaian
    -0.44
     églises
    -0.38
     aplicable
    -0.38
     Configuración
    -0.38
     électroniques
    -0.37
     leçons
    -0.37
     verksamhet
    -0.37
     journées
    -0.37
     juridiques
    -0.36
     économies
    -0.35
    POSITIVE LOGITS
    +#+
    0.77
     AssemblyCompany
    0.65
    AndEndTag
    0.63
     Infórmanos
    0.58
     ویکی‌پدی
    0.58
    tisgarh
    0.57
    OGND
    0.56
     Administrativna
    0.55
    ंदीखरीदारी
    0.54
    __(/*!
    0.52
    Activations Density 0.788%

    No Known Activations