© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7109
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to navigation and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -1.15
    fjspx
    -0.88
    ValueStyle
    -0.86
    تقاوى
    -0.86
    setVerticalGroup
    -0.82
    ThroughAttribute
    -0.78
    optionalTypeArgs
    -0.76
     useCallback
    -0.76
    ParallelGroup
    -0.75
    WireFormatLite
    -0.72
    POSITIVE LOGITS
    _
    0.44
    Clik
    0.42
     pennies
    0.40
     ||=
    0.40
     maxHeight
    0.40
    "
    0.39
     arac
    0.38
     väx
    0.38
     actualité
    0.38
    EL
    0.38
    Activations Density 0.220%

    No Known Activations