© 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. 23-GEMMASCOPE-RES-16K
    6. 8225
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouvez
    -0.50
    reactstrap
    -0.47
    Filmografie
    -0.45
    igeon
    -0.45
    CreateModel
    -0.43
    alamualaikum
    -0.42
    SerializeField
    -0.42
    tamaan
    -0.42
    styleType
    -0.42
     aján
    -0.41
    POSITIVE LOGITS
     history
    3.95
    history
    3.42
     History
    3.16
    History
    3.08
     HISTORY
    2.99
    HISTORY
    2.78
     histories
    2.73
     sejarah
    2.56
     historia
    2.53
     historical
    2.40
    Activations Density 0.576%

    No Known Activations