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. 20-GEMMASCOPE-RES-131K
    6. 122879
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and financial figures

    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_20/width_131k/average_l0_114
    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
    <i>
    -0.55
     appunto
    -0.54
     :
    -0.50
     ocasião
    -0.50
     pernas
    -0.48
     borboleta
    -0.47
     Vogt
    -0.46
     Velasco
    -0.46
    seits
    -0.46
     mães
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.73
    $\$
    0.71
     $\$
    0.66
     myſelf
    0.65
     Verſ
    0.64
     itſelf
    0.64
     ſche
    0.63
     Monfieur
    0.63
     themſelves
    0.62
    ">$
    0.61
    Activations Density 0.030%

    No Known Activations