© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3048
    Prev
    Next
    INDEX
    Explanations

    numerical values in a structured data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?,
    -0.65
     समीक्षक
    -0.60
    Identyfik
    -0.57
     كومونز
    -0.52
    деб
    -0.52
     hany
    -0.51
     distanciation
    -0.51
    =\""
    -0.49
     veng
    -0.48
    цездатний
    -0.48
    POSITIVE LOGITS
    !*\
    0.59
    |()
    0.59
    :][
    0.58
    使
    0.58
    ValueStyle
    0.57
     ExecuteAsync
    0.57
     createContext
    0.55
    ViewFeatures
    0.54
    dafx
    0.54
    pidou
    0.53
    Activations Density 0.366%

    No Known Activations