© 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. 18-GEMMASCOPE-RES-16K
    11. 1918
    Prev
    Next
    INDEX
    Explanations

    numerical data and punctuation, indicating potential financial figures or statistics

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

    Punctuation mark followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    detecting sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.77
     purpoſe
    -1.54
     ་་
    -1.52
     myſelf
    -1.52
     pleaſure
    -1.44
     Jefus
    -1.44
     doubtnut
    -1.44
     Houſe
    -1.43
     houſe
    -1.42
     ſtate
    -1.41
    POSITIVE LOGITS
     
    1.21
     (
    1.13
     a
    1.03
     “
    0.98
     "
    0.97
    :
    0.93
    ,
    0.93
    !
    0.87
    .
    0.84
     «
    0.84
    Activations Density 0.329%

    No Known Activations