© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 194
    Prev
    Next
    INDEX
    Explanations

    specific mentions of locations or places

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

    Followed by a location

    np_acts-logits-general · gemini-2.0-flash

    specific locations

    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
    PrototypeOf
    -0.58
    bootstrapcdn
    -0.55
    deutschland
    -0.55
     viewType
    -0.55
     @"/
    -0.54
     الدولى
    -0.53
    mybatisplus
    -0.52
     ComVisible
    -0.52
    Tracce
    -0.50
     ſever
    -0.50
    POSITIVE LOGITS
    
    0.70
    queryInterface
    0.66
     Hong
    0.63
     Paglinawan
    0.62
    afficheront
    0.60
     San
    0.54
    ₦
    0.51
    ()?;
    0.51
    icksburg
    0.50
    ⓘ
    0.50
    Activations Density 1.955%

    No Known Activations