© 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. 123
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" within the text

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

    the start of documents or sections indicating new content

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

    and News Florida New Q

    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
     همچنین
    -1.25
     alfo
    -1.14
     also
    -1.10
     Also
    -1.05
    Also
    -1.04
    also
    -1.02
     ayrıca
    -1.02
     alſo
    -1.01
     myſelf
    -1.00
     также
    -1.00
    POSITIVE LOGITS
     they
    1.27
     we
    1.04
     you
    1.00
     it
    1.00
     he
    0.98
     there
    0.85
     she
    0.84
    they
    0.67
     autorytatywna
    0.66
     I
    0.65
    Activations Density 0.153%

    No Known Activations