© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11553
    Prev
    Next
    INDEX
    Explanations

    curly braces and various control flow indicators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.78
     myſelf
    -0.72
     BoxDecoration
    -0.67
     Akismet
    -0.66
     domestique
    -0.64
    Kariera
    -0.64
     Jefus
    -0.64
    RenderAtEndOf
    -0.63
     Beller
    -0.62
     Majefty
    -0.62
    POSITIVE LOGITS
     Draw
    0.61
    newBuilder
    0.59
    帖最后由
    0.55
    SerializedSize
    0.54
     DRAW
    0.54
     braccia
    0.53
     Walkover
    0.52
     "..\..\
    0.52
     Which
    0.52
     draw
    0.51
    Activations Density 0.533%

    No Known Activations