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. 12-GEMMASCOPE-RES-16K
    6. 15254
    Prev
    Next
    INDEX
    Explanations

    references to hormones and their biological actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Wiktionnaire
    -0.57
     Virtu
    -0.55
     felix
    -0.54
    óch
    -0.53
     للاسماء
    -0.53
    ési
    -0.53
     neuropathy
    -0.52
    commod
    -0.51
    yers
    -0.51
    atelle
    -0.51
    POSITIVE LOGITS
     hormones
    1.34
     hormone
    1.23
     Hormones
    1.16
    complexContent
    1.13
     hormonal
    1.07
     Hormone
    1.06
     propOrder
    1.00
    Horm
    0.99
    horm
    0.99
    sterone
    0.97
    Activations Density 0.756%

    No Known Activations