© 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. 21-GEMMASCOPE-RES-16K
    11. 14895
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "the" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ussis
    -0.48
     deschis
    -0.46
    klád
    -0.46
     prostředí
    -0.46
    synthesize
    -0.45
     BoxDecoration
    -0.44
    cazione
    -0.43
     direttamente
    -0.42
    bootstrapcdn
    -0.42
     tarko
    -0.42
    POSITIVE LOGITS
     globe
    1.15
     spectrum
    1.02
    spectrum
    0.82
    globe
    0.79
     espectro
    0.77
     length
    0.75
     world
    0.73
     continent
    0.73
     board
    0.73
     country
    0.72
    Activations Density 0.144%

    No Known Activations