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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 69531
    Prev
    Next
    INDEX
    Explanations

    key terms related to criminal incidents and law enforcement activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    AccessorTable
    -0.58
    رشف
    -0.57
    Rhestr
    -0.52
     للاسماء
    -0.50
    ItemBackground
    -0.47
    httphttps
    -0.46
    dcterms
    -0.45
     Signalez
    -0.44
    phorbia
    -0.44
    jadinya
    -0.44
    POSITIVE LOGITS
    libft
    0.44
    Unmarshaller
    0.40
     Tal
    0.36
    urier
    0.35
     MANUAL
    0.34
    年生
    0.33
     translational
    0.33
     TRANSL
    0.32
    テレ
    0.32
     suburban
    0.32
    Activations Density 0.007%

    No Known Activations