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. 7361
    Prev
    Next
    INDEX
    Explanations

    statements about legal analysis and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Referanser
    -0.72
    LEncoder
    -0.68
    )['
    -0.64
     ویکی‌پدیا
    -0.59
    ()['
    -0.58
    ()%
    -0.55
    /$',
    -0.55
    きに
    -0.55
    ':'
    -0.55
    ()"
    -0.54
    POSITIVE LOGITS
     however
    4.00
    however
    3.42
     entanto
    3.25
     però
    3.08
     though
    2.90
     cependant
    2.68
    However
    2.68
     tuttavia
    2.59
     însă
    2.53
     όμως
    2.53
    Activations Density 1.655%

    No Known Activations