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. 0-GEMMASCOPE-RES-16K
    6. 3308
    Prev
    Next
    INDEX
    Explanations

    instances of the word "much" indicating degree or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.71
     ſeveral
    -0.64
     dandy
    -0.62
     Houſe
    -0.61
     Margin
    -0.61
     faſt
    -0.61
     Monfieur
    -0.60
     légende
    -0.59
     ſmall
    -0.58
     ſever
    -0.56
    POSITIVE LOGITS
     Much
    1.21
    Much
    1.18
     much
    0.86
    much
    0.85
     viel
    0.70
     MUCH
    0.67
     mucho
    0.61
     Cow
    0.59
    Exists
    0.58
    CloseOperation
    0.57
    Activations Density 0.099%

    No Known Activations