© 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. 20-GEMMASCOPE-RES-16K
    11. 10575
    Prev
    Next
    INDEX
    Explanations

    references to HTML and special characters

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

    HTML/XML character entities (e.g., ')

    np_acts-logits-general · gemini-2.0-flash

    HTML entities and older text formatting

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ,
    -0.64
    (
    -0.60
     –
    -0.60
     (
    -0.60
       
    -0.57
      
    -0.57
    —
    -0.56
        
    -0.54
    <eos>
    -0.54
    …
    -0.53
    POSITIVE LOGITS
    ftagPool
    1.01
    httphttps
    0.94
    <tfoot>
    0.89
    ſelves
    0.85
    GEBURTSDATUM
    0.85
     GenerationType
    0.84
     greateſt
    0.82
    sidemargin
    0.81
    ParallelGroup
    0.81
     Majefty
    0.80
    Activations Density 0.145%

    No Known Activations