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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122682
    Prev
    Next
    INDEX
    Explanations

    references to economic policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     MainAxisSize
    -0.61
    Rujuakan
    -0.58
     Numerade
    -0.55
    󠁣
    -0.53
    RTEX
    -0.53
    adaptiveStyles
    -0.52
    <_>
    -0.51
     мәкал
    -0.49
    EDEFAULT
    -0.47
    InputTagHelper
    -0.47
    POSITIVE LOGITS
    oliber
    0.49
     neoliberal
    0.42
    றி
    0.37
    Globalization
    0.37
     economic
    0.35
     Aust
    0.34
     Globalization
    0.33
     globalization
    0.32
     privatization
    0.31
     åt
    0.30
    Activations Density 0.062%

    No Known Activations