Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7896
    Prev
    Next
    INDEX
    Explanations

    references to public services, health, and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Irán
    -0.54
     História
    -0.52
     Herramientas
    -0.52
     Diseño
    -0.50
     Tecnología
    -0.50
     conversión
    -0.49
     complementos
    -0.48
     Economía
    -0.48
     Ingeniería
    -0.47
     Soporte
    -0.47
    POSITIVE LOGITS
     Public
    1.22
    Public
    1.20
     public
    1.13
     PUBLIC
    1.08
    public
    0.97
     publick
    0.92
    PUBLIC
    0.90
     publicly
    0.81
     publics
    0.80
     öffentlichen
    0.78
    Activations Density 0.088%

    No Known Activations