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. 33-GEMMASCOPE-RES-131K
    6. 65950
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or statistics related to quantities and comparisons

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.69
     autorytatywna
    -0.55
     мәкал
    -0.54
     otomatig
    -0.52
    Autoritní
    -0.52
    posedge
    -0.52
     للاسماء
    -0.51
     betweenstory
    -0.50
    FunctionFlags
    -0.50
    uxxxx
    -0.49
    POSITIVE LOGITS
    olybden
    0.36
     céu
    0.34
     rag
    0.32
     fiyat
    0.32
    getSelectedItem
    0.31
     Fraser
    0.31
    beiros
    0.31
    OrEqualTo
    0.31
    :+:
    0.30
    baru
    0.30
    Activations Density 0.002%

    No Known Activations