© 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. 0-GEMMASCOPE-RES-65K
    11. 10059
    Prev
    Next
    INDEX
    Explanations

    instances of the word "opening" and variations of the term in different contexts

    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
     Kün
    -0.59
    DataAnnotations
    -0.58
    stranger
    -0.53
    yang
    -0.52
    ちょう
    -0.52
    mặt
    -0.50
     stranger
    -0.50
     sánchez
    -0.48
    ಂದ
    -0.48
    enteric
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.86
    +#+#
    0.75
    GeneratedMessage
    0.69
     CreateTagHelper
    0.69
    Opening
    0.68
     fis
    0.68
    webElementGuid
    0.68
    FormTagHelper
    0.67
     Wharf
    0.66
     оригіналу
    0.66
    Activations Density 0.049%

    No Known Activations