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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 965
    Prev
    Next
    INDEX
    Explanations

    references to traditional medicine and health-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    you
    -0.71
     you
    -0.63
    お客様
    -0.59
     people
    -0.59
     guys
    -0.58
     inimes
    -0.58
     लोगों
    -0.57
     peoples
    -0.56
     moje
    -0.56
     everybody
    -0.56
    POSITIVE LOGITS
     themselves
    1.85
     their
    1.73
    themselves
    1.64
    their
    1.48
    Their
    1.38
     Their
    1.21
     ihres
    1.15
     ihrer
    1.13
     leur
    1.13
     ihren
    1.11
    Activations Density 1.334%

    No Known Activations