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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5053
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and feelings about family dynamics

    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
     inmediato
    -0.71
     immédi
    -0.70
     immédiatement
    -0.69
     aussitôt
    -0.65
     immediate
    -0.61
    CDCl
    -0.60
     Immediately
    -0.58
     immediatamente
    -0.58
    RSpec
    -0.58
    즉
    -0.57
    POSITIVE LOGITS
     finally
    3.11
    finally
    2.71
     Finally
    2.59
     eventually
    2.54
    Finally
    2.52
     finalmente
    2.46
    Eventually
    2.28
     Finalmente
    2.27
     Eventually
    2.27
    eventually
    2.18
    Activations Density 0.511%

    No Known Activations