Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16243
    Prev
    Next
    INDEX
    Explanations

    references to file types, specifically related to programming or data formats

    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
    TRIBUTES
    -0.66
    IPAC
    -0.64
    قاط
    -0.62
    itron
    -0.61
    bbons
    -0.61
     Braun
    -0.61
    liminaries
    -0.60
     (;;
    -0.59
     onOptions
    -0.59
    ecause
    -0.59
    POSITIVE LOGITS
    ft
    2.30
    FT
    1.90
     ft
    1.61
     FT
    1.32
    fts
    1.25
    Ft
    1.23
    ht
    1.11
    fting
    1.02
    FTS
    0.99
    fte
    0.99
    Activations Density 0.105%

    No Known Activations