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. 16-GEMMASCOPE-RES-16K
    6. 12985
    Prev
    Next
    INDEX
    Explanations

    corporate names, specifically those related to finance and industry

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

    preceding "Corporation", "Corp", "Group" or "Capital"

    np_acts-logits-general · gemini-2.0-flash

    company names followed by Corp or Corporation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     s
    -0.55
    2
    -0.50
    M
    -0.46
    舎
    -0.46
     M
    -0.43
     mesto
    -0.43
     sociais
    -0.41
     nazionali
    -0.40
     senhor
    -0.39
    star
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.89
     Conſ
    0.85
    mybatisplus
    0.82
     JAXBElement
    0.81
    windowFixed
    0.81
     Reſ
    0.81
     Roskov
    0.79
    dafx
    0.79
    OGND
    0.78
     Houſe
    0.78
    Activations Density 0.464%

    No Known Activations