© 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. 22-GEMMASCOPE-RES-16K
    11. 11568
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to options in a selection or decision-making context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "option" or "options"

    np_acts-logits-general · gemini-2.0-flash

    options or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.56
    writeField
    -0.56
    }{*}{}
    -0.52
    CrossRef
    -0.50
    XmlAccessorType
    -0.49
    happen
    -0.48
    ViewFeatures
    -0.47
    SerializedName
    -0.47
    dealloc
    -0.47
    dymyr
    -0.47
    POSITIVE LOGITS
     Options
    1.33
     options
    1.26
     OPTION
    1.10
     option
    1.10
    options
    1.09
     onOptions
    1.06
     OPTIONS
    1.05
    OPTION
    1.00
     Option
    0.99
     Choices
    0.98
    Activations Density 0.167%

    No Known Activations