Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2213
    Prev
    Next
    INDEX
    Explanations

    references to locations in London

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "of," "in," "at," or "on."

    np_acts-logits-general · gemini-2.0-flash

    london places and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering evals
    london

    No Comments

    Negative Logits
    
    -0.81
     Waray
    -0.66
    posedge
    -0.64
     VIAF
    -0.63
     Aloha
    -0.58
    nasium
    -0.55
     Replay
    -0.55
    MemoryWarning
    -0.54
    prnewswire
    -0.54
     WaitForSeconds
    -0.53
    POSITIVE LOGITS
     London
    1.03
    London
    0.84
     london
    0.75
     Londres
    0.73
    london
    0.73
     Londra
    0.72
     tube
    0.71
     Lond
    0.70
     Hammers
    0.70
     Westminster
    0.69
    Activations Density 0.134%

    No Known Activations