© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2343
    Prev
    Next
    INDEX
    Explanations

    the concept of "real" as it relates to authenticity or sincerity 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 @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judiciaire
    -0.74
     mourut
    -0.70
     perpétu
    -0.70
     pouvoit
    -0.69
     obicei
    -0.69
     auroit
    -0.68
     efectivamente
    -0.68
     inderdaad
    -0.66
     inoxydable
    -0.65
     feroit
    -0.64
    POSITIVE LOGITS
     real
    3.85
     Real
    3.40
    real
    3.35
    Real
    3.22
     REAL
    2.97
    REAL
    2.84
     реаль
    2.14
     reales
    1.99
     reale
    1.88
     réel
    1.80
    Activations Density 0.114%

    No Known Activations