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. 25-GEMMASCOPE-RES-16K
    6. 3516
    Prev
    Next
    INDEX
    Explanations

    geographical references and locations, particularly related to Budapest and its historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     különböz
    -0.67
    httphttps
    -0.66
    AsUp
    -0.63
     NSCoder
    -0.60
     felb
    -0.60
    PreferredItem
    -0.60
    Calif
    -0.60
    IndentedString
    -0.59
     eszköz
    -0.57
     néz
    -0.57
    POSITIVE LOGITS
     Hungarian
    1.45
     Hungary
    1.40
     Budapest
    1.38
    Hungarian
    1.18
    Budapest
    1.17
    Hungary
    1.16
     Magyar
    1.09
     Hung
    1.06
     Buda
    1.04
     budapest
    1.02
    Activations Density 0.068%

    No Known Activations