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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1861
    Prev
    Next
    INDEX
    Explanations

    instances of financial terms and metrics related to banking and insurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Whilst
    -1.17
     Whilst
    -1.14
     tyres
    -1.13
    labour
    -1.10
     realised
    -1.10
     analysed
    -1.08
     specialises
    -1.05
     recognised
    -1.04
    Analyse
    -1.04
     organised
    -1.02
    POSITIVE LOGITS
     parlor
    1.03
     confiable
    1.03
     favors
    1.00
     favorably
    0.96
     flavorful
    0.96
    ônicos
    0.95
     theaters
    0.93
     flavors
    0.93
     flavor
    0.92
     theater
    0.91
    Activations Density 2.256%

    No Known Activations