© 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. 3-GEMMASCOPE-RES-16K
    6. 11643
    Prev
    Next
    INDEX
    Explanations

    terms related to bishops and episcopal hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PhysRevD
    -0.71
    المكان
    -0.58
     Ukrainian
    -0.55
    Diweddarwch
    -0.50
    PRNewswire
    -0.49
     bestaande
    -0.49
    شهاد
    -0.48
    показания
    -0.48
     peculiarly
    -0.47
     Obrador
    -0.46
    POSITIVE LOGITS
     <=",
    0.72
    Bishop
    0.66
     Bishop
    0.63
    AccessException
    0.62
    Naissance
    0.60
    webElementGuid
    0.60
     BISHOP
    0.60
     snippetHide
    0.60
    "},
    
    0.59
    "])
    
    0.59
    Activations Density 1.137%

    No Known Activations