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. 53732
    Prev
    Next
    INDEX
    Explanations

    specific mathematical and scientific symbols, terms, and references related to equations and formulas used in data analysis

    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
     فريبيس
    -0.53
    enumii
    -0.52
    ագրություններ
    -0.51
    intios
    -0.49
    SequentialGroup
    -0.49
    󠁢
    -0.49
    󠁧
    -0.48
    LEncoder
    -0.48
    rboles
    -0.47
    MethodManager
    -0.47
    POSITIVE LOGITS
    endregion
    0.38
     elb
    0.38
    createCanvas
    0.35
    Попис
    0.35
    יתוף
    0.35
    ofür
    0.34
     Pion
    0.33
     Sebab
    0.33
     Jah
    0.32
     allAfrica
    0.32
    Activations Density 0.243%

    No Known Activations