© 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. 3-GEMMASCOPE-RES-16K
    6. 5699
    Prev
    Next
    INDEX
    Explanations

    phrases related to software and configuration options

    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
    gridx
    -0.78
    Sucesor
    -0.76
    DeleteBehavior
    -0.72
    SourceChecksum
    -0.70
    BagLayout
    -0.69
    AsUp
    -0.67
     LatLng
    -0.66
     BIBSYS
    -0.66
    CrossRef
    -0.66
     Walkover
    -0.65
    POSITIVE LOGITS
    options
    2.64
    Options
    2.54
     Options
    2.14
    OPTIONS
    2.01
     options
    1.97
     OPTIONS
    1.75
    Option
    1.68
    OPTION
    1.56
     Option
    1.56
    setOptions
    1.50
    Activations Density 0.077%

    No Known Activations