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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9452
    Prev
    Next
    INDEX
    Explanations

    numerical data and specifications related to technical or product details

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

    Appearing after "I-7" or other numbers

    np_acts-logits-general · gemini-2.0-flash

    corridor, index, camera, format, SUV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    لي
    -0.48
     
    -0.47
    urally
    -0.43
     pé
    -0.42
    ----------
    
    -0.42
    зо
    -0.41
    ura
    -0.41
    ENAS
    -0.41
    ствие
    -0.41
    ECO
    -0.41
    POSITIVE LOGITS
    ″
    1.40
    ′
    1.18
     ExecuteAsync
    1.16
    DockStyle
    1.14
    Personensuche
    1.13
    
    1.10
    ValueStyle
    1.08
    ″]
    1.07
     Савезне
    1.06
     propOrder
    1.05
    Activations Density 1.194%

    No Known Activations