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

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 9444
    Prev
    Next
    INDEX
    Explanations

    references to "original" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.82
     Réponses
    -0.79
     decoradas
    -0.77
    
    -0.74
     <=",
    -0.73
    amqp
    -0.71
     okuyayım
    -0.71
    nestjs
    -0.70
    XtraGrid
    -0.70
     Foxx
    -0.69
    POSITIVE LOGITS
     original
    2.40
    Original
    2.29
     ORIGINAL
    2.22
     Original
    2.20
    original
    2.14
    ORIGINAL
    2.00
     originals
    1.93
     orig
    1.80
     originale
    1.68
     Originals
    1.65
    Activations Density 0.039%

    No Known Activations