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. 24-GEMMASCOPE-RES-131K
    6. 727
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.82
    GEBURTSDATUM
    -0.75
    Datuak
    -0.75
     estekak
    -0.74
    webElementXpaths
    -0.73
     kaarangay
    -0.68
    hone
    -0.65
    ⏃
    -0.65
    原始内容存档于
    -0.65
    Билгалдахарш
    -0.65
    POSITIVE LOGITS
     Inscrivez
    0.42
     vœ
    0.41
     asupra
    0.39
     acestui
    0.35
     acompañado
    0.35
     tandis
    0.33
     astfel
    0.33
     folhe
    0.33
     acestei
    0.32
     inmig
    0.32
    Activations Density 0.037%

    No Known Activations