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. 3-GEMMASCOPE-RES-16K
    6. 11011
    Prev
    Next
    INDEX
    Explanations

    mentions of science or scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIAF
    -0.83
     paroisse
    -0.82
    VIAF
    -0.82
     circonst
    -0.79
     Wikiseite
    -0.77
    ulmuş
    -0.73
     ATTORNEY
    -0.72
     amitié
    -0.71
     noDo
    -0.68
     roulant
    -0.68
    POSITIVE LOGITS
     science
    3.18
     Science
    3.12
    Science
    2.87
    science
    2.84
     SCIENCE
    2.80
    SCIENCE
    2.46
     sciences
    2.29
     Sci
    2.24
    cience
    2.19
     Sciences
    2.13
    Activations Density 0.049%

    No Known Activations