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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1127
    Prev
    Next
    INDEX
    Explanations

    references to transitions and changes in systems, particularly in research and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    changing or moving

    np_acts-logits-general · gemini-2.0-flash

    transitioning to new states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raffredd
    -0.55
    (!__
    -0.54
     BeautifulSoup
    -0.54
     geométrico
    -0.53
     urbanas
    -0.51
    وام
    -0.51
     possesso
    -0.47
    HasAnnotation
    -0.45
     salvajes
    -0.45
    tagHelperRunner
    -0.44
    POSITIVE LOGITS
     switch
    2.64
     transition
    2.62
     switching
    2.38
     switched
    2.28
     transitioning
    2.24
     transitioned
    2.22
     Transition
    2.20
     shift
    2.19
     transitions
    2.14
     Switch
    2.13
    Activations Density 0.709%

    No Known Activations