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. 18-GEMMASCOPE-RES-16K
    6. 3613
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical concepts related to resistors and circuit analysis

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

    Followed by punctuation or conjunction

    np_acts-logits-general · gemini-2.0-flash

    mathematical rounding and calculations

    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
     often
    -0.59
     sometimes
    -0.56
    往往
    -0.51
     oftentimes
    -0.51
     many
    -0.49
     Sometimes
    -0.45
     Often
    -0.45
     usually
    -0.42
     gewisser
    -0.42
     primarily
    -0.42
    POSITIVE LOGITS
     autorytatywna
    1.00
     beträgt
    1.00
    webElementXpaths
    0.90
    RegistryLite
    0.89
    RegressionTest
    0.82
     wynosi
    0.80
    windowFixed
    0.79
     risulta
    0.77
    enterOuterAlt
    0.77
     lautet
    0.76
    Activations Density 1.057%

    No Known Activations