© 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. 20-GEMMASCOPE-RES-65K
    6. 710
    Prev
    Next
    INDEX
    Explanations

    variants of the word "twist" in various contexts

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

    references to twists or unexpected developments in narratives

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

    twist drill, twist ending, twist tie, twist rates

    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
     ReactDOM
    -0.68
    MLLoader
    -0.64
    PMailer
    -0.63
     חיצוניים
    -0.61
     <<<<<<<<<<<<<<
    -0.61
    MemoryWarning
    -0.60
    WebKit
    -0.60
    تفصیلات
    -0.60
     caufe
    -0.59
     Substanz
    -0.59
    POSITIVE LOGITS
    Twist
    0.95
     Twist
    0.95
     twists
    0.85
     twist
    0.83
    Twisted
    0.79
    twist
    0.77
     twisting
    0.73
     Twisted
    0.69
    Ẫ
    0.65
     twisted
    0.65
    Activations Density 0.016%

    No Known Activations