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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9274
    Prev
    Next
    INDEX
    Explanations

    references to mistakes or errors related to scientific work and their corrections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.68
    windowFixed
    -0.59
     AssemblyProduct
    -0.55
    sizeCache
    -0.49
    الحياه
    -0.49
    Demografía
    -0.48
     Administrativna
    -0.47
    urlpatterns
    -0.47
     actionBar
    -0.47
     BitmapFactory
    -0.46
    POSITIVE LOGITS
     mistakes
    2.40
     mistake
    2.36
     errors
    2.18
     error
    2.14
     Mistakes
    2.02
     Mistake
    1.90
     erreur
    1.84
     errori
    1.83
     erreurs
    1.83
     errores
    1.78
    Activations Density 0.837%

    No Known Activations