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. 15596
    Prev
    Next
    INDEX
    Explanations

    references to job opportunities and associated benefits

    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
     Wiktionnaire
    -0.59
     Grüsse
    -0.44
     powst
    -0.40
     australiano
    -0.40
     Infórmanos
    -0.40
    vestres
    -0.39
     producciones
    -0.38
     plástica
    -0.38
    ">//
    -0.38
     lavado
    -0.37
    POSITIVE LOGITS
     sales
    0.96
     Sales
    0.96
     salesmen
    0.91
    Sales
    0.87
     salesperson
    0.86
     salespeople
    0.85
     salesman
    0.85
    sales
    0.85
     SALES
    0.77
    SALES
    0.69
    Activations Density 0.335%

    No Known Activations