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. 5-GEMMASCOPE-RES-16K
    6. 8582
    Prev
    Next
    INDEX
    Explanations

    specific details about events, including dates, times, and availability information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.68
    исленность
    -0.67
    tvguidetime
    -0.66
    TagMode
    -0.65
    stonia
    -0.64
     AssemblyCulture
    -0.64
    rature
    -0.63
    Спасылкі
    -0.61
     intStringLen
    -0.59
    +#+#
    -0.59
    POSITIVE LOGITS
    lapsingToolbar
    0.56
    CrossRef
    0.55
     kasarigan
    0.52
     initComponents
    0.49
     autorytatywna
    0.48
    Gemeinden
    0.48
    __':
    
    0.47
     betale
    0.46
    ⓘ
    0.46
     disambiguazione
    0.45
    Activations Density 0.184%

    No Known Activations