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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3516
    Prev
    Next
    INDEX
    Explanations

    references to 'deals' and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LoggerFactory
    -0.58
     Flagstaff
    -0.51
    iburg
    -0.49
     Northumberland
    -0.49
     Савезне
    -0.49
     students
    -0.48
     Khr
    -0.47
    gypti
    -0.47
     Pinterest
    -0.47
     perlahan
    -0.47
    POSITIVE LOGITS
     deal
    2.11
     Deal
    1.98
    Deal
    1.97
    deal
    1.96
     DEAL
    1.81
     deals
    1.76
     Deals
    1.63
    deals
    1.58
    DEAL
    1.56
    Deals
    1.53
    Activations Density 0.141%

    No Known Activations