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. 15-GEMMASCOPE-RES-16K
    6. 2482
    Prev
    Next
    INDEX
    Explanations

    features and specifications related to multifunctional audio devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.76
    DockStyle
    -0.73
    RenderAtEndOf
    -0.69
     CreateTagHelper
    -0.66
    setVerticalGroup
    -0.65
    ódnica
    -0.63
    MessageDigest
    -0.62
    Brainz
    -0.62
     المعيارى
    -0.61
    parsedMessage
    -0.60
    POSITIVE LOGITS
    Features
    0.59
    MENAFN
    0.58
    ConverterFactory
    0.55
     features
    0.54
     convenient
    0.53
    features
    0.52
     ✅
    0.50
     white
    0.50
     Features
    0.49
    ✅
    0.49
    Activations Density 0.101%

    No Known Activations