© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 16187
    Prev
    Next
    INDEX
    Explanations

    references to locations and entities in Connecticut and its history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.88
    ReusableCell
    -0.85
    таратура
    -0.83
     imageNamed
    -0.80
     &___
    -0.79
     Wheatley
    -0.78
     odkazy
    -0.74
    +#+#
    -0.74
    WithIdentifier
    -0.71
    pertino
    -0.70
    POSITIVE LOGITS
     Iraqi
    1.12
     Iraq
    1.06
    Iraq
    1.01
     Baghdad
    0.94
     العراق
    0.92
     عراق
    0.85
    Ira
    0.83
    Connecticut
    0.83
     Irak
    0.79
     Saddam
    0.77
    Activations Density 0.893%

    No Known Activations