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
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 117
    Prev
    Next
    INDEX
    Explanations

    groups of individuals at higher risk for certain health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -0.35
     Ebers
    -0.30
     moment
    -0.29
     ITS
    -0.29
     Its
    -0.28
     his
    -0.28
     itself
    -0.28
    theo
    -0.27
     let
    -0.27
    Its
    -0.27
    POSITIVE LOGITS
     themſelves
    0.76
     myſelf
    0.76
    SequentialGroup
    0.74
     queſta
    0.72
    istoitu
    0.71
     canst
    0.71
     CanadaChoose
    0.71
    ArgumentParser
    0.69
     fometimes
    0.68
     للمعارف
    0.67
    Activations Density 0.091%

    No Known Activations