© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 605
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical data, particularly in the context of scientific research and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical identifiers and codes commonly associated with academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic citations or specific links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    事
    -0.43
     pick
    -0.40
     home
    -0.38
     أع
    -0.36
    te
    -0.36
     thuis
    -0.35
     sapere
    -0.35
     hole
    -0.35
    ђа
    -0.34
    ão
    -0.34
    POSITIVE LOGITS
    Autoritní
    1.10
    StoryboardSegue
    1.08
     autorytatywna
    1.04
    abestanden
    1.04
     ComVisible
    1.03
     jScrollPane
    1.01
    IsContent
    0.97
    MemoryWarning
    0.96
    XmlAccessorType
    0.93
    GraphicsUnit
    0.92
    Activations Density 0.030%

    No Known Activations