© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10303
    Prev
    Next
    INDEX
    Explanations

    references to numeric values or measurements

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

    Tokens often followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    foreign words

    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
      
    -0.72
     «
    -0.67
    ,
    -0.65
    .
    -0.62
     "
    -0.60
     to
    -0.57
     “
    -0.56
    et
    -0.56
     as
    -0.56
     in
    -0.56
    POSITIVE LOGITS
    verwijspagina
    1.21
     للمعارف
    1.13
     Мексичка
    1.12
     Italijanski
    1.10
    Geplaatst
    1.09
    <bos>
    1.09
     autorytatywna
    1.08
    Демографія
    1.07
     Савезне
    1.06
     ujednoznacz
    1.04
    Activations Density 0.436%

    No Known Activations