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. 40774
    Prev
    Next
    INDEX
    Explanations

    concepts related to realism and practical decision-making

    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
     Pot
    -0.26
    Cursor
    -0.26
     Agassi
    -0.26
     cust
    -0.26
     erw
    -0.25
     Mito
    -0.25
     Brat
    -0.25
     guste
    -0.24
    </b>
    -0.24
     reg
    -0.24
    POSITIVE LOGITS
     racional
    0.87
     rational
    0.87
     rationally
    0.81
     rationality
    0.79
     sensible
    0.78
    Rational
    0.74
    冷静
    0.73
    rational
    0.73
     inteligente
    0.70
     AssemblyCompany
    0.70
    Activations Density 0.081%

    No Known Activations