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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 6222
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific measurements and quantitative analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gero
    -0.45
     du
    -0.43
    badlogic
    -0.43
     Adu
    -0.43
     Dess
    -0.43
    ותו
    -0.43
     '%
    -0.43
    Dess
    -0.42
    <table>
    -0.42
     Lo
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.82
     &___
    0.74
     betweenstory
    0.74
     allAfrica
    0.69
     للمعارف
    0.65
    таратура
    0.64
     lenker
    0.63
     ostavi
    0.62
    ISupport
    0.59
    agisse
    0.59
    Activations Density 0.708%

    No Known Activations