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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2792
    Prev
    Next
    INDEX
    Explanations

    references to historical events and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.94
     فريبيس
    -0.81
     Majefty
    -0.79
     للمعارف
    -0.77
     للاسماء
    -0.77
    QMetaType
    -0.76
    ChildScrollView
    -0.76
    tagHelperRunner
    -0.76
    DockStyle
    -0.75
    IndentedString
    -0.75
    POSITIVE LOGITS
     AD
    1.12
    AD
    0.90
     BC
    0.79
     CE
    0.73
    BC
    0.62
     Anno
    0.62
     ad
    0.60
    Anno
    0.59
    ad
    0.59
     Ad
    0.54
    Activations Density 0.263%

    No Known Activations