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. 13-GEMMASCOPE-RES-16K
    6. 10291
    Prev
    Next
    INDEX
    Explanations

    punctuation and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     San
    -0.62
     Савезне
    -0.61
     der
    -0.61
     Sta
    -0.59
    ('/:
    -0.58
     san
    -0.56
     Sal
    -0.55
    UNGE
    -0.55
    antar
    -0.54
    elfth
    -0.54
    POSITIVE LOGITS
    ValueStyle
    0.80
    ReusableCell
    0.76
    bootstrapcdn
    0.76
    SequentialGroup
    0.73
    ConstraintMaker
    0.73
    NegativeButton
    0.71
     Shakspeare
    0.71
     snippetHide
    0.70
     dieß
    0.69
     suivants
    0.69
    Activations Density 0.354%

    No Known Activations