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. 20-GEMMASCOPE-RES-16K
    6. 14102
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial processes and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***!
    -0.75
     mergeFrom
    -0.68
    RenderAtEndOf
    -0.66
    principalColumn
    -0.65
     تضيفلها
    -0.64
    MigrationBuilder
    -0.59
    HtmlAttribute
    -0.58
     defaultstate
    -0.58
    LookAnd
    -0.57
    OpenHelper
    -0.57
    POSITIVE LOGITS
    зулта
    0.56
     estates
    0.56
     الدولى
    0.52
     espionage
    0.52
     sectors
    0.51
     sector
    0.50
    ági
    0.50
     estate
    0.48
     defStyle
    0.48
    patine
    0.48
    Activations Density 0.049%

    No Known Activations