© 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. 14-GEMMASCOPE-RES-16K
    6. 8221
    Prev
    Next
    INDEX
    Explanations

    repeated sequences or patterns in numerical or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.74
    kaw
    -0.74
    ruptedException
    -0.66
     Gren
    -0.66
     Ek
    -0.65
    edonia
    -0.65
     Srin
    -0.64
    /**
    -0.63
    */,
    -0.63
    %;
    
    -0.63
    POSITIVE LOGITS
    +#+
    1.23
     Houſe
    1.00
     myſelf
    0.98
     ſtate
    0.97
     itſelf
    0.96
     Jefus
    0.96
     greateſt
    0.94
     Eſ
    0.94
     Anſ
    0.93
     ſta
    0.93
    Activations Density 0.960%

    No Known Activations