© 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. 1-GEMMASCOPE-RES-16K
    11. 7358
    Prev
    Next
    INDEX
    Explanations

    terms related to self-assessment and contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.73
    ècie
    -0.65
    ViewImports
    -0.63
     NSCoder
    -0.61
     whor
    -0.59
     tây
    -0.58
    testcase
    -0.56
     @"/
    -0.56
     Audiodateien
    -0.55
     cage
    -0.55
    POSITIVE LOGITS
     reflect
    4.09
     reflected
    4.03
     reflecting
    3.89
     reflection
    3.84
     Reflect
    3.75
     reflects
    3.71
    reflect
    3.63
    Reflect
    3.39
     reflections
    3.31
     Reflection
    3.19
    Activations Density 0.104%

    No Known Activations