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

    Neuronpedia

    APICircuit 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52997
    Prev
    Next
    INDEX
    Explanations

    key terms related to fundraising events

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

    construction, sites, Session, held, magazine, report, February

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -1.18
    Personendaten
    -1.15
     Савезне
    -1.09
    GraphicsUnit
    -0.96
     ujednoznacz
    -0.95
     bezeichneter
    -0.94
     Мексичка
    -0.91
    بوابة
    -0.89
     lenker
    -0.88
    RenderAtEndOf
    -0.88
    POSITIVE LOGITS
     our
    0.88
    !
    0.73
     please
    0.69
    our
    0.67
    我们的
    0.65
     Please
    0.65
    我們的
    0.63
    Please
    0.62
     nossa
    0.61
     naše
    0.60
    Activations Density 0.167%

    No Known Activations