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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14629
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurement and analysis

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

    followed by "of" or "in"

    np_acts-logits-general · gemini-2.0-flash

    positively describing processes or changes

    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
     ligiloj
    -0.64
    outSlope
    -0.62
    cookieParser
    -0.54
    SpringBootTest
    -0.52
    tizado
    -0.51
    WebServlet
    -0.49
    Комментарии
    -0.49
    нциклопе
    -0.49
    loroethane
    -0.49
    pecto
    -0.48
    POSITIVE LOGITS
     extensively
    1.69
     correctly
    1.67
     adequately
    1.66
     thoroughly
    1.66
     properly
    1.66
     differently
    1.65
     efficiently
    1.64
     nicely
    1.61
     accurately
    1.58
     comprehensively
    1.53
    Activations Density 1.416%

    No Known Activations