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. 22-GEMMASCOPE-RES-16K
    6. 5899
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to educational institutions and geographical locations

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

    Cities, districts, or towns

    np_acts-logits-general · gemini-2.0-flash

    places named after cities or districts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -1.03
    Datuak
    -0.94
    CodeAttribute
    -0.88
     متعلقه
    -0.87
     betweenstory
    -0.80
    fillType
    -0.78
    脚注の使い方
    -0.75
    stateProvider
    -0.74
     referrerpolicy
    -0.74
    numerusform
    -0.73
    POSITIVE LOGITS
     city
    1.05
     City
    1.03
     town
    0.97
     Town
    0.85
     district
    0.82
    City
    0.78
     ciudad
    0.76
     città
    0.75
     Stadt
    0.74
    city
    0.74
    Activations Density 0.153%

    No Known Activations