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. 12487
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to video formats and frame rates

    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
    RectangleBorder
    -0.73
    וויק
    -0.64
    GraphicsUnit
    -0.62
    ंदीखरीदारी
    -0.61
    InputBorder
    -0.61
    DeleteBehavior
    -0.58
    principalColumn
    -0.52
     typelib
    -0.51
     newOwner
    -0.51
     שוליים
    -0.50
    POSITIVE LOGITS
     frames
    1.61
     frame
    1.59
     animation
    1.53
     Frames
    1.48
     Frame
    1.42
     Animation
    1.35
    frame
    1.33
    frames
    1.33
     animations
    1.31
     FRAME
    1.28
    Activations Density 0.238%

    No Known Activations