© 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. 3-GEMMASCOPE-RES-16K
    11. 7867
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of rejection or lack of importance

    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
    AutoScale
    -0.65
     cref
    -0.53
    ondra
    -0.50
    habe
    -0.49
     merci
    -0.49
    setImageBitmap
    -0.49
     bicolor
    -0.48
    請繼續往下閱讀
    -0.48
    Erreferentziak
    -0.47
     sẻ
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.75
    Portail
    0.73
     محفوظة
    0.64
    tagHelperRunner
    0.62
    TestingModule
    0.61
    UIControlState
    0.58
     foal
    0.58
     Italij
    0.58
    openhauer
    0.58
     nahilalakip
    0.57
    Activations Density 0.289%

    No Known Activations