© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7011
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and emoticons, indicating emotional expression

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

    Smiley faces and colons

    np_acts-logits-general · gemini-2.0-flash

    emoticons like :D and :P

    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
     disambiguazione
    -0.92
     resourceCulture
    -0.90
     للمعارف
    -0.88
    出版年
    -0.86
     Савезне
    -0.79
     snippetHide
    -0.76
     wireType
    -0.75
    
    -0.75
     ExecuteAsync
    -0.74
     تانيه
    -0.70
    POSITIVE LOGITS
    D
    1.07
    P
    0.91
    p
    0.72
    )
    0.68
     D
    0.66
    (.
    0.61
    -)
    0.61
    O
    0.60
    ))
    0.60
    ).
    0.58
    Activations Density 0.134%

    No Known Activations