© 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. 17-GEMMASCOPE-RES-16K
    11. 9514
    Prev
    Next
    INDEX
    Explanations

    quantitative statistics and numerical data

    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
    
    -0.83
     initComponents
    -0.80
     <=",
    -0.79
    WithIOException
    -0.74
    IsContent
    -0.73
     JpaRepository
    -0.70
    AndEndTag
    -0.68
     intStringLen
    -0.66
    MessageOf
    -0.65
    存于互联网档案馆
    -0.64
    POSITIVE LOGITS
     unbelievable
    1.66
     incredible
    1.65
     astounding
    1.56
     astonishing
    1.52
     amazing
    1.48
    incredible
    1.46
    Incredible
    1.44
     Incredible
    1.38
     staggering
    1.38
    amazing
    1.30
    Activations Density 0.359%

    No Known Activations