© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7478
    Prev
    Next
    INDEX
    Explanations

    details about the specifications and features of products, particularly focusing on design elements and technical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.38
    Speaker
    -0.38
     चीज़ों
    -0.37
     thái
    -0.36
    ربای
    -0.35
    OWN
    -0.35
    ----</
    -0.35
    CROSSTALK
    -0.35
    fjspx
    -0.34
     pédagog
    -0.34
    POSITIVE LOGITS
     included
    0.77
     ability
    0.75
     inclusion
    0.73
     lack
    0.70
     company
    0.67
     designers
    0.65
     default
    0.65
     inability
    0.63
     supplied
    0.62
     price
    0.62
    Activations Density 0.434%

    No Known Activations