© 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. 16-GEMMASCOPE-RES-16K
    11. 8459
    Prev
    Next
    INDEX
    Explanations

    geographical names and locations

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

    Preceding a place, profession, or nationality

    np_acts-logits-general · gemini-2.0-flash

    locations followed by professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inherits
    -0.52
     partea
    -0.46
     européens
    -0.42
     îng
    -0.41
     
    -0.40
     ferrocarril
    -0.40
    []
    -0.40
     laikā
    -0.40
     particulières
    -0.38
    льної
    -0.38
    POSITIVE LOGITS
    NUMX
    0.99
    WriteTagHelper
    0.99
    IntoConstraints
    0.94
    Portale
    0.93
    abestanden
    0.86
    tanleria
    0.86
     незавершена
    0.85
    脚注の使い方
    0.84
     AspNetCore
    0.84
     Мексичка
    0.84
    Activations Density 0.214%

    No Known Activations