© 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. 4-GEMMASCOPE-RES-16K
    11. 976
    Prev
    Next
    INDEX
    Explanations

    expressions related to the condition of being alive or well-being

    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
    StructEnd
    -0.93
    Devi
    -0.78
    addContainerGap
    -0.77
    #__
    -0.76
     Grüsse
    -0.75
    Jereo
    -0.75
     يتيمه
    -0.74
     ContentValues
    -0.74
     Stepan
    -0.73
     ModelRenderer
    -0.71
    POSITIVE LOGITS
     alive
    1.96
     ALIVE
    1.90
     Alive
    1.88
    alive
    1.57
    Alive
    1.51
     vivos
    0.83
    ById
    0.77
     awake
    0.76
    ByKey
    0.72
    活着
    0.70
    Activations Density 0.068%

    No Known Activations