© 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. 4-GEMMASCOPE-RES-16K
    6. 15166
    Prev
    Next
    INDEX
    Explanations

    code-related structures and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jScrollPane
    -0.76
     CURIAM
    -0.54
    GUY
    -0.51
    يكب
    -0.51
    ropriate
    -0.51
    zyści
    -0.49
     proposées
    -0.47
     exogenous
    -0.47
     classiques
    -0.47
     señora
    -0.47
    POSITIVE LOGITS
     AssemblyVersion
    0.75
    terase
    0.67
    lgari
    0.64
     للمعارف
    0.60
    AccessorTable
    0.59
     AssemblyTitle
    0.57
    dotenv
    0.56
    ớt
    0.54
    playable
    0.54
    setViewportView
    0.53
    Activations Density 0.650%

    No Known Activations