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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 983
    Prev
    Next
    INDEX
    Explanations

    leadership styles that emphasize employee involvement and satisfaction

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

    leadership styles and factors related to employee engagement and organization goals

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

    threats or challenges

    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
     يتيمه
    -0.70
    VersionUID
    -0.62
     للمعارف
    -0.60
     թվական
    -0.58
    issory
    -0.57
    IVersion
    -0.54
    wapV
    -0.54
     sàng
    -0.53
     assuré
    -0.52
    ंदीखरीदारी
    -0.52
    POSITIVE LOGITS
    astify
    0.63
     amenazas
    0.62
     gyhoeddwyd
    0.53
     Threats
    0.51
    makeConstraints
    0.50
    OGND
    0.50
    Begriffsklä
    0.50
     amea
    0.50
     Exacts
    0.49
    dientes
    0.47
    Activations Density 0.078%

    No Known Activations