© 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. 11731
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases expressing needs, abilities, or actions

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

    French/Russian words indicating requests or possibilities

    np_acts-logits-general · gemini-2.0-flash

    can and must

    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
     Jefus
    -0.73
     Eſ
    -0.70
     Monfieur
    -0.68
    增加了
    -0.68
    bbene
    -0.67
     myſelf
    -0.66
     Efq
    -0.66
     pleaſure
    -0.66
     Majefty
    -0.66
    带来了
    -0.66
    POSITIVE LOGITS
     being
    1.07
     Being
    0.85
    Being
    0.84
     having
    0.82
    being
    0.79
     taking
    0.73
     getting
    0.73
     BEING
    0.72
     take
    0.67
     make
    0.66
    Activations Density 0.060%

    No Known Activations