Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 25-GEMMASCOPE-RES-16K
    6. 12566
    Prev
    Next
    INDEX
    Explanations

    terms related to endocrine disruption and toxicity in chemical substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.69
    الحياه
    -0.51
     robbed
    -0.50
     kompres
    -0.50
    kuli
    -0.48
    cure
    -0.48
     remittance
    -0.47
    
    -0.47
    ript
    -0.47
     đông
    -0.47
    POSITIVE LOGITS
     exposure
    1.00
     exposures
    0.93
     Exposure
    0.92
    Exposure
    0.87
    exposure
    0.87
     toxicological
    0.78
     EXPOSURE
    0.77
     Expos
    0.77
     toxicity
    0.72
     toxicology
    0.69
    Activations Density 1.064%

    No Known Activations