© 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. 449
    Prev
    Next
    INDEX
    Explanations

    words related to duration or longevity

    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
    CTE
    -0.88
     Pixie
    -0.81
     Gere
    -0.81
     Chiron
    -0.80
     Henson
    -0.79
    yczą
    -0.76
     GNA
    -0.75
     pix
    -0.74
     Dougherty
    -0.73
     Exposition
    -0.73
    POSITIVE LOGITS
     last
    1.54
    last
    1.38
     Last
    1.37
     LAST
    1.35
    Last
    1.29
     lasts
    1.28
    LAST
    1.25
     lasted
    1.21
    lasting
    1.08
     Lasting
    1.04
    Activations Density 0.091%

    No Known Activations