© 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. 1-GEMMASCOPE-RES-16K
    6. 12656
    Prev
    Next
    INDEX
    Explanations

    terms related to "preferred" or favored options in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.86
    AndEndTag
    -0.85
    providedIn
    -0.84
    ReferenceEquals
    -0.77
    TypedDataSet
    -0.74
    contentLoaded
    -0.73
    makeText
    -0.71
    hasMoreElements
    -0.70
    complexContent
    -0.64
    titleMargin
    -0.64
    POSITIVE LOGITS
     appreciated
    1.61
     preferred
    1.59
     favored
    1.44
    preferred
    1.38
     accepted
    1.38
     respected
    1.36
     cherished
    1.28
     valued
    1.28
     liked
    1.27
     desired
    1.25
    Activations Density 0.142%

    No Known Activations