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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38799
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and health contexts, especially focusing on conditions related to pregnancy and childbirth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poète
    -0.44
    ">//
    -0.38
     doute
    -0.37
    Viitteet
    -0.37
     Herkunft
    -0.36
     smallest
    -0.36
     AssemblyVersion
    -0.36
    __':
    
    -0.35
    Enllaces
    -0.35
     Luar
    -0.35
    POSITIVE LOGITS
     jsPsych
    0.52
    PreferredItem
    0.46
     MainAxisSize
    0.45
    AtIndexPath
    0.42
    newtheorem
    0.42
     Chwiliwch
    0.40
    columnHeader
    0.39
     mapStateToProps
    0.36
     rhestr
    0.36
    المناصب
    0.36
    Activations Density 0.126%

    No Known Activations