© 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. 8021
    Prev
    Next
    INDEX
    Explanations

    key terms related to advantages, problems, and differences in various contexts

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

    preceding "problem," "reason," "advantage", or "thing"

    np_acts-logits-general · gemini-2.0-flash

    main/biggest/primary point or problem

    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
     кӀ
    -0.62
     صوتيه
    -0.62
     للمعارف
    -0.47
    DOCTYPE
    -0.46
    quela
    -0.46
    providedIn
    -0.45
     otomatig
    -0.44
     Lijst
    -0.44
    various
    -0.43
    ことができました
    -0.43
    POSITIVE LOGITS
     thing
    1.29
     reason
    1.26
     question
    1.02
     drawback
    0.98
     concern
    0.98
     highlight
    0.96
     problem
    0.94
     focus
    0.90
    reason
    0.89
     aim
    0.89
    Activations Density 0.350%

    No Known Activations