© 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. 167
    Prev
    Next
    INDEX
    Explanations

    segments of text that indicate the start of a new section or paragraph

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

    the beginning of sentences or paragraphs

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

    finite difference

    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
    ,
    -0.72
     a
    -0.71
     and
    -0.65
     in
    -0.65
     of
    -0.64
     on
    -0.64
     as
    -0.63
     her
    -0.62
     et
    -0.60
     val
    -0.59
    POSITIVE LOGITS
     itſelf
    1.33
     ſeveral
    1.27
     myſelf
    1.26
     Efq
    1.19
     whoſe
    1.18
    ſelves
    1.18
     Monfieur
    1.17
     Houſe
    1.15
     Reſ
    1.13
     raiſ
    1.11
    Activations Density 0.409%

    No Known Activations