© 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. 20-GEMMASCOPE-RES-16K
    11. 15165
    Prev
    Next
    INDEX
    Explanations

    technical terms and criteria related to medical research and evaluations

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

    Software or criteria version numbers

    np_acts-logits-general · gemini-2.0-flash

    software version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.95
    AnchorStyles
    -0.83
    ьаж
    -0.74
    تقاوى
    -0.72
    Portale
    -0.70
    parsedMessage
    -0.69
     مشين
    -0.69
    oredCriteria
    -0.65
    Tikang
    -0.64
    WebVitals
    -0.62
    POSITIVE LOGITS
     version
    2.16
     v
    2.07
     Version
    2.07
    Version
    1.84
    version
    1.84
    v
    1.74
     versión
    1.69
     versions
    1.65
     VERSION
    1.65
     versão
    1.61
    Activations Density 0.954%

    No Known Activations