© 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. 15-GEMMASCOPE-RES-16K
    11. 9653
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups 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 @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muß
    -1.01
     läßt
    -0.94
     skall
    -0.89
     müßte
    -0.81
     mußte
    -0.79
     daß
    -0.78
     Moslem
    -0.75
    ・・・・・
    -0.68
     Usted
    -0.63
     mußten
    -0.63
    POSITIVE LOGITS
     tryna
    1.10
     shitty
    1.06
    Alright
    1.04
     weirdly
    1.02
     goddamn
    0.95
     tbh
    0.94
     whatnot
    0.94
     fucked
    0.94
    NameInMap
    0.94
     idk
    0.93
    Activations Density 2.453%

    No Known Activations