© 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. 10664
    Prev
    Next
    INDEX
    Explanations

    references to shared resources or collaborative elements in context

    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
     Warte
    -0.45
     pukul
    -0.45
    Officials
    -0.45
    ânsito
    -0.44
    umbai
    -0.43
     autorytatywna
    -0.43
     Koop
    -0.42
    mentation
    -0.42
    Lunch
    -0.42
     Bisnis
    -0.41
    POSITIVE LOGITS
     guests
    0.97
     Sleeps
    0.95
     Guests
    0.91
     sleeps
    0.90
     Hosts
    0.86
     linens
    0.85
    Guests
    0.85
     hosts
    0.83
     Superhost
    0.80
    guests
    0.78
    Activations Density 0.047%

    No Known Activations