© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 14672
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to medicine, especially safety warnings and instructions for drug usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.65
     Italijanski
    -0.57
    tagHelperRunner
    -0.56
    CloseOperation
    -0.55
    rungsseite
    -0.54
    URATION
    -0.53
    Hentet
    -0.53
    resave
    -0.52
    AutoresizingMask
    -0.51
    mybatisplus
    -0.51
    POSITIVE LOGITS
     itſelf
    0.96
     poffible
    0.76
     myſelf
    0.72
    typeorm
    0.70
     houſe
    0.68
    ſelf
    0.68
     purpoſe
    0.67
     whoſe
    0.67
     himſelf
    0.67
     themſelves
    0.66
    Activations Density 0.377%

    No Known Activations