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. 103225
    Prev
    Next
    INDEX
    Explanations

    numerical data and specifically monetary values in the text

    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
     تكبرها
    -0.50
    +#+#
    -0.41
     voluntarily
    -0.35
    AndEndTag
    -0.35
    Something
    -0.35
     volunt
    -0.35
     coś
    -0.35
    oids
    -0.35
    Yar
    -0.35
    cipline
    -0.35
    POSITIVE LOGITS
    WriteTagHelper
    0.61
    XtraEditors
    0.52
    Hentet
    0.49
     equivalent
    0.48
    RectangleBorder
    0.47
    AnchorStyles
    0.46
    TargetException
    0.46
    bootstrapcdn
    0.46
    RefNanny
    0.46
    NameInMap
    0.45
    Activations Density 0.035%

    No Known Activations