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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1889
    Prev
    Next
    INDEX
    Explanations

    technical terms and methodologies related to computational chemistry and density functional theory (DFT) calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.71
    انيف
    -0.55
    oplayer
    -0.54
    PhysRevD
    -0.52
    AndEndTag
    -0.49
    ഷ
    -0.49
    echy
    -0.48
    expandindo
    -0.47
     tắt
    -0.46
    Engineers
    -0.44
    POSITIVE LOGITS
     electronic
    0.66
     Hart
    0.65
     calculations
    0.60
     calculation
    0.58
     électroniques
    0.58
    Източници
    0.58
     CreateTagHelper
    0.57
     Electronic
    0.57
    addCriterion
    0.57
     DFT
    0.57
    Activations Density 0.793%

    No Known Activations