© 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. 23-GEMMASCOPE-RES-16K
    11. 4173
    Prev
    Next
    INDEX
    Explanations

    content related to sharing and best practices in research and forensic applications

    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
    KommentareTeilen
    -0.69
     VizieR
    -0.60
    Hauptartikel
    -0.59
    こち
    -0.57
    ThroughAttribute
    -0.53
     CanadaChoose
    -0.48
    лючение
    -0.48
     تضيفلها
    -0.47
    homonymie
    -0.47
    fortawesome
    -0.47
    POSITIVE LOGITS
     best
    2.57
    best
    2.31
    Best
    2.07
     Best
    2.05
     BEST
    1.74
    BEST
    1.73
     practices
    1.69
     practice
    1.54
    最佳
    1.48
     Practices
    1.47
    Activations Density 0.315%

    No Known Activations