Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6152
    Prev
    Next
    INDEX
    Explanations

    instances of dashes or hyphens in various contexts

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

    Text separated by em-dashes

    np_acts-logits-general · gemini-2.0-flash

    em dashes, en dashes, hyphens

    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
     --
    -1.14
    —
    -0.98
    --
    -0.92
     —
    -0.89
     –
    -0.84
    ---
    -0.84
     ---
    -0.79
     -
    -0.74
     שוליים
    -0.74
    --"
    -0.72
    POSITIVE LOGITS
    '])){
    
    0.71
      
    0.69
    awtextra
    0.65
    /=
    0.64
    页面存档备份
    0.62
     ​​
    0.62
    verwijspagina
    0.60
    ']>
    0.59
    '),
    
    0.59
     ')
    
    0.59
    Activations Density 0.319%

    No Known Activations