© 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. 25-GEMMASCOPE-RES-16K
    11. 1436
    Prev
    Next
    INDEX
    Explanations

    context related to celebrity lifestyles and exclusives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighborhood
    -0.82
     neighbor
    -0.74
     neighbors
    -0.73
    Neighbors
    -0.71
     mußten
    -0.71
     intermédiaire
    -0.70
     dignité
    -0.70
     esposo
    -0.70
     mußte
    -0.69
    AVOR
    -0.69
    POSITIVE LOGITS
    Whilst
    1.33
     Whilst
    1.31
    initialise
    1.17
     whilst
    1.17
     (£
    1.08
     prioritise
    1.06
     realising
    1.05
     realisation
    1.05
     recognisable
    1.03
    organised
    1.03
    Activations Density 0.586%

    No Known Activations