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. 8-GEMMASCOPE-RES-16K
    6. 4687
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öns
    -0.62
     Kost
    -0.53
    itz
    -0.52
     cứ
    -0.49
    jz
    -0.48
     Injectable
    -0.48
    Климат
    -0.47
     Races
    -0.46
     AdapterView
    -0.46
    TUN
    -0.46
    POSITIVE LOGITS
    ंदीखरीदारी
    1.11
    UnusedPrivate
    0.87
     betweenstory
    0.86
    UrlResolution
    0.82
     otomatig
    0.81
     تضيفلها
    0.81
    TintMode
    0.80
    FieldBuilder
    0.80
    ViewFeatures
    0.78
     Infórmanos
    0.77
    Activations Density 0.149%

    No Known Activations