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. 24-GEMMASCOPE-RES-16K
    6. 2296
    Prev
    Next
    INDEX
    Explanations

    references to healthcare topics and societal issues related to gender and emotional challenges

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

    followed by "either"

    np_acts-logits-general · gemini-2.0-flash

    not this ... either

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    而非
    -0.67
     uVar
    -0.65
    vician
    -0.63
    
    -0.62
    而不是
    -0.56
    istoitu
    -0.54
    GIVEREF
    -0.54
    UpInside
    -0.54
    AutoField
    -0.53
     Мексичка
    -0.52
    POSITIVE LOGITS
     either
    3.29
    either
    2.79
     Either
    2.61
    Either
    2.55
     entweder
    2.11
     heller
    1.66
    ITHER
    1.66
    要么
    1.48
     enten
    1.44
     либо
    1.35
    Activations Density 0.268%

    No Known Activations