© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13681
    Prev
    Next
    INDEX
    Explanations

    references to simulations or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.42
     intervenciones
    -0.41
    Viited
    -0.41
     الرياضيه
    -0.39
     pessoais
    -0.39
    rivit
    -0.38
    Життєпис
    -0.38
    ofType
    -0.37
    stagland
    -0.36
     publicidad
    -0.36
    POSITIVE LOGITS
     Sim
    3.33
    Sim
    3.22
     sim
    3.22
     SIM
    2.86
    SIM
    2.72
    sim
    2.64
     sims
    2.30
     Сим
    2.13
    sims
    2.02
     Sims
    1.91
    Activations Density 0.289%

    No Known Activations