© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12092
    Prev
    Next
    INDEX
    Explanations

    exclamatory and emphatic expressions related to specific events or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GHIJKLM
    -0.49
    المناصب
    -0.46
    Datuak
    -0.44
    RectangleBorder
    -0.44
    Gön
    -0.42
    nables
    -0.42
    selaer
    -0.42
    MENAFN
    -0.42
    מד
    -0.41
     كومونز
    -0.41
    POSITIVE LOGITS
     Pingback
    1.04
    LikeLike
    0.81
     Comment
    0.78
     comment
    0.74
     Leave
    0.74
    Comment
    0.74
     commenting
    0.73
     komentar
    0.72
     commented
    0.72
     Reply
    0.71
    Activations Density 0.190%

    No Known Activations