© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10595
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes and their specifications in digital networking and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    روابط
    -0.53
     كمان
    -0.53
     enfans
    -0.52
     ホイール
    -0.47
     uska
    -0.47
    hogy
    -0.47
     Ressources
    -0.45
    leyebilirsiniz
    -0.45
    řevě
    -0.45
     Seconde
    -0.45
    POSITIVE LOGITS
    󠁿
    1.10
    EndContext
    0.98
    μβρίου
    0.91
    interopRequire
    0.89
    CJK
    0.87
    StructEnd
    0.85
     سكانية
    0.83
    Hauptartikel
    0.80
    endphp
    0.80
    <>();
    
    0.78
    Activations Density 13.782%

    No Known Activations