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. 18-GEMMASCOPE-RES-16K
    6. 15106
    Prev
    Next
    INDEX
    Explanations

    names of geographical locations and associated entities

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

    Central American countries

    np_acts-logits-general · gemini-2.0-flash

    Central American countries and Mexico

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Woj
    -0.61
    Woj
    -0.58
    naphthal
    -0.57
    __*/
    -0.57
     Andalucía
    -0.52
     Staten
    -0.50
    čar
    -0.50
     Otero
    -0.49
     Muslim
    -0.49
    España
    -0.48
    POSITIVE LOGITS
     Mexico
    0.71
     Guatem
    0.71
     hond
    0.70
     Meksiku
    0.70
     Hond
    0.70
    Mexico
    0.69
    +#+#
    0.68
     MEXICO
    0.67
     MEX
    0.67
     Oaxaca
    0.66
    Activations Density 0.111%

    No Known Activations