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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 5561
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and associated attributes

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

    Languages, numbers, and codes

    np_acts-logits-general · gemini-2.0-flash

    Ward, languages, numbers, cans, Cobalt, ratio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.66
    verifyException
    -0.66
    CodeAttribute
    -0.64
    Tembelea
    -0.63
    FunctionFlags
    -0.63
     فريبيس
    -0.63
    Lähteet
    -0.61
    
    -0.60
    出版年
    -0.60
    +#+#
    -0.59
    POSITIVE LOGITS
     also
    1.06
     też
    0.88
     тоже
    0.87
     também
    0.83
     също
    0.82
     tampoco
    0.81
     likewise
    0.81
     också
    0.81
     también
    0.80
    also
    0.78
    Activations Density 1.861%

    No Known Activations