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. 1707
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and data points related to sports outcomes

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

    Numbers, especially in the context of scores or records

    np_acts-logits-general · gemini-2.0-flash

    numbers and scores

    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
    出版年
    -0.68
    
    -0.54
    sbereich
    -0.51
    :✨
    -0.51
     group
    -0.49
    EventLoop
    -0.47
    devamını
    -0.46
     vPvB
    -0.44
    يميديا
    -0.44
    μβρίου
    -0.43
    POSITIVE LOGITS
    BeginContext
    0.71
    SequentialGroup
    0.71
    ValueStyle
    0.64
     BoxFit
    0.62
    ConstraintMaker
    0.60
    ollectionView
    0.58
    styleType
    0.55
    "]').
    0.55
    "]];
    0.54
    adaptiveStyles
    0.54
    Activations Density 0.062%

    No Known Activations