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. 0-GEMMASCOPE-RES-16K
    6. 8006
    Prev
    Next
    INDEX
    Explanations

    instances of the word "original."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.73
    ígenes
    -0.68
     AssemblyTitle
    -0.64
    bestos
    -0.61
     pigeons
    -0.60
     defStyleAttr
    -0.58
     vetorial
    -0.58
    IGraphics
    -0.56
     Witkin
    -0.56
     MediatR
    -0.56
    POSITIVE LOGITS
     original
    1.31
    original
    1.13
    Original
    1.06
     Original
    1.04
     ORIGINAL
    0.97
    ORIGINAL
    0.83
     oorspron
    0.81
     originals
    0.79
     оригинал
    0.72
    原始
    0.72
    Activations Density 0.103%

    No Known Activations