© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1746
    Prev
    Next
    INDEX
    Explanations

    references to a specific chemical compound or category denoted by "di" in its name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.73
     Jefus
    -0.73
    vea
    -0.72
     Meda
    -0.72
     meda
    -0.70
     محفوظة
    -0.69
     ende
    -0.68
     itſelf
    -0.67
     fure
    -0.67
     purpoſe
    -0.64
    POSITIVE LOGITS
     di
    2.27
     Di
    2.03
    Di
    1.89
     DI
    1.43
    di
    1.27
    DI
    1.15
     Dietz
    1.07
     Dib
    1.04
    Dib
    1.02
     diarrhoea
    0.99
    Activations Density 0.072%

    No Known Activations