Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12521
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial products and lending processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.50
    Conversely
    -0.45
     perhaps
    -0.45
     آنچه
    -0.44
     Conversely
    -0.44
     otomatig
    -0.44
     pungkas
    -0.44
     informée
    -0.44
     ostensibly
    -0.43
     portions
    -0.41
    POSITIVE LOGITS
     different
    0.79
     equipments
    0.77
     researches
    0.77
     few
    0.75
     softwares
    0.74
     evidences
    0.74
    Nowadays
    0.73
    different
    0.70
    Different
    0.69
     Nowadays
    0.69
    Activations Density 1.810%

    No Known Activations