© 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. 10699
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their emotional context in the text

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

    Emoticons using colons and parentheses

    np_acts-logits-general · gemini-2.0-flash

    emoticons and informal punctuation

    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
     ExecuteAsync
    -0.73
    IntoConstraints
    -0.70
    ImageContext
    -0.66
     للمعارف
    -0.64
    Abitanti
    -0.62
     snippetHide
    -0.59
    Qual
    -0.59
    InputBorder
    -0.57
    Kontrola
    -0.56
    posób
    -0.55
    POSITIVE LOGITS
    D
    0.64
    wink
    0.57
    P
    0.55
    ::
    0.54
    nodoc
    0.53
    سكري
    0.53
    haha
    0.51
    lol
    0.51
     Haha
    0.51
    ::::
    0.50
    Activations Density 0.097%

    No Known Activations