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. 25-GEMMASCOPE-RES-16K
    6. 1919
    Prev
    Next
    INDEX
    Explanations

    phrases and variations related to "roll" or "rolling."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.52
    lação
    -0.50
    OGND
    -0.49
    relative
    -0.49
     pymongo
    -0.47
    litch
    -0.47
     Pantheon
    -0.46
    Faker
    -0.46
    keteers
    -0.46
    цезда
    -0.45
    POSITIVE LOGITS
     dice
    0.67
     Royce
    0.67
     يتيمه
    0.66
    coaster
    0.62
    Royce
    0.62
     snowball
    0.59
    dice
    0.58
     coaster
    0.56
     thunder
    0.56
    ANTLR
    0.56
    Activations Density 0.274%

    No Known Activations