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. 3-GEMMASCOPE-RES-16K
    6. 10047
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.73
    日閲覧
    -0.66
    InstrumentedTest
    -0.60
    !")
    
    -0.59
    发表于
    -0.59
     Signalez
    -0.57
     defStyleAttr
    -0.54
    taste
    -0.54
     Chon
    -0.54
     jspb
    -0.54
    POSITIVE LOGITS
    TargetException
    0.71
    三百
    0.68
    رشف
    0.67
     Hundreds
    0.66
     hundred
    0.66
    五百
    0.65
    Hundreds
    0.64
     Thousands
    0.63
    Thousands
    0.63
     ddelweddau
    0.63
    Activations Density 0.250%

    No Known Activations