© 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. 9100
    Prev
    Next
    INDEX
    Explanations

    elements related to community, social interactions, and emotional connections

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

    Follows "thing," "letter," or plural nouns

    np_acts-logits-general · gemini-2.0-flash

    thing is

    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
    おり
    -0.56
    __.__
    -0.51
    naio
    -0.50
     ErrIntOverflow
    -0.50
    uesa
    -0.49
    ]='\
    -0.49
    thus
    -0.49
    ご了承
    -0.48
     nulla
    -0.47
     thus
    -0.47
    POSITIVE LOGITS
     wasn
    1.24
     didn
    1.19
     isn
    1.12
     weren
    1.11
     wouldn
    1.10
     doesn
    1.07
     aren
    1.05
     shouldn
    1.03
     hasn
    1.02
     ain
    1.02
    Activations Density 0.454%

    No Known Activations