Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 660
    Prev
    Next
    INDEX
    Explanations

    programming elements related to control structures and data manipulation

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

    coding structures that include functions and loops

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

    programming loops and iteration

    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
     for
    -0.72
     Infórmanos
    -0.59
     für
    -0.57
    ValueStyle
    -0.52
    ]")]
    -0.50
     для
    -0.49
     hierfür
    -0.49
    Билгалдахарш
    -0.48
     JAXBElement
    -0.47
    AddTagHelper
    -0.47
    POSITIVE LOGITS
    foreach
    1.59
     foreach
    1.17
     each
    0.76
    EACH
    0.75
    FORE
    0.73
    each
    0.70
     EVERY
    0.68
     every
    0.68
    Fore
    0.64
    KEYCODE
    0.63
    Activations Density 0.017%

    No Known Activations