© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 34
    Prev
    Next
    INDEX
    Explanations

    phrases indicating qualifications or conditions related to actions or events

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

    instances of the token "<bos>"

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

    as, since, although

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Houſe
    -0.51
     herself
    -0.47
     itſelf
    -0.46
     economico
    -0.46
    vieja
    -0.45
     Alva
    -0.44
    ąg
    -0.44
     Pergamon
    -0.44
     damska
    -0.44
    jalá
    -0.42
    POSITIVE LOGITS
     there
    1.56
     they
    1.33
     it
    1.22
    there
    1.20
     we
    1.06
     he
    0.97
     THERE
    0.96
     There
    0.90
    There
    0.87
     although
    0.85
    Activations Density 0.139%

    No Known Activations