© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9974
    Prev
    Next
    INDEX
    Explanations

    opportunities for change or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.85
    ResumeLayout
    -0.78
     pageContext
    -0.76
    webElement
    -0.69
    XmlIgnore
    -0.67
    ⓧ
    -0.66
    orianCalendar
    -0.64
    XmlAccessorType
    -0.64
    Encyklopedia
    -0.61
     iNdEx
    -0.60
    POSITIVE LOGITS
     chance
    0.60
     setSelected
    0.55
    UMBIA
    0.54
     cornerstone
    0.51
     opportunity
    0.51
     getSelected
    0.50
    mpe
    0.50
    核心
    0.49
     مر
    0.49
     escu
    0.49
    Activations Density 0.117%

    No Known Activations