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 - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14437
    Prev
    Next
    INDEX
    Explanations

    date-related terms, particularly focusing on the month of October and its associated numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.76
     March
    -0.68
    MARCH
    -0.66
     disponibilités
    -0.66
    hå
    -0.65
     bodyParser
    -0.63
    cstdlib
    -0.63
     AssemblyProduct
    -0.62
     WrestleMania
    -0.62
    имущества
    -0.62
    POSITIVE LOGITS
     October
    1.04
    October
    1.03
    Oct
    1.01
     pumpkin
    1.00
     oktober
    0.99
     Oct
    0.98
     autumn
    0.97
    oct
    0.96
     Halloween
    0.96
     oct
    0.95
    Activations Density 0.225%

    No Known Activations