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. 6508
    Prev
    Next
    INDEX
    Explanations

    terms related to smoothness, particularly in reference to surfaces or textures

    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
    yntaxException
    -0.67
     متعلقه
    -0.66
    typeorm
    -0.60
    NOPQRST
    -0.55
    OGND
    -0.51
    espère
    -0.49
     pilas
    -0.49
    ndel
    -0.48
    TagMode
    -0.47
    corrhi
    -0.47
    POSITIVE LOGITS
     Smooth
    1.30
     smooth
    1.26
    Smooth
    1.24
    smooth
    1.20
     smoother
    1.14
     smoothness
    1.13
     SMO
    1.08
     transition
    1.03
     smoothly
    1.01
     lisse
    1.00
    Activations Density 0.081%

    No Known Activations