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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12704
    Prev
    Next
    INDEX
    Explanations

    terms and names associated with governmental and institutional entities

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

    after names of European institutions

    np_acts-logits-general · gemini-2.0-flash

    universities and research institutes

    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
     
    -0.55
    (
    -0.52
     dis
    -0.51
    <eos>
    -0.49
    逆
    -0.47
    ,
    -0.46
     sort
    -0.45
     that
    -0.45
     rec
    -0.45
     ...
    -0.45
    POSITIVE LOGITS
     للمعارف
    1.06
    出版年
    1.04
    ]--;
    0.85
    
    0.82
     Italijanski
    0.82
    StoryboardSegue
    0.82
    RenderAtEndOf
    0.80
    GraphicsUnit
    0.78
     StatelessWidget
    0.77
    קישורים
    0.76
    Activations Density 0.105%

    No Known Activations