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. 18-GEMMASCOPE-RES-16K
    6. 10439
    Prev
    Next
    INDEX
    Explanations

    terms related to file conversion and extraction processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.83
     defStyleAttr
    -0.72
    tagHelperRunner
    -0.68
     الحره
    -0.68
    存于互联网档案馆
    -0.66
     Signalez
    -0.65
    oredCriteria
    -0.64
    IGraphics
    -0.62
    InjectAttribute
    -0.62
     WebDriverWait
    -0.61
    POSITIVE LOGITS
     Facebook
    0.54
    cely
    0.54
     multiple
    0.53
     converting
    0.52
     convert
    0.52
     efficiently
    0.50
     Google
    0.50
     PDF
    0.50
    Multiple
    0.50
     Android
    0.50
    Activations Density 0.541%

    No Known Activations