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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1130
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions related to people, their traits, and their interactions in a social context

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

    Followed by punctuation or prepositions

    np_acts-logits-general · gemini-2.0-flash

    emojis 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
    tagez
    -0.69
     muligt
    -0.68
    明明
    -0.64
     skolen
    -0.62
     separado
    -0.58
    ArrowToggle
    -0.56
    だからこそ
    -0.56
     skolan
    -0.56
     Grecs
    -0.55
     oamenii
    -0.55
    POSITIVE LOGITS
     ;-)
    0.92
     ;)
    0.84
     😉
    0.83
    😜
    0.69
    😉
    0.69
     :-)
    0.67
     ͡°
    0.65
    ;-)
    0.64
     الرياضيه
    0.64
    可不是
    0.63
    Activations Density 0.727%

    No Known Activations