© 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. 3-GEMMASCOPE-RES-16K
    11. 8030
    Prev
    Next
    INDEX
    Explanations

    references to extreme or severe conditions or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BindView
    -0.67
     sputtering
    -0.64
     tidur
    -0.64
     fiducia
    -0.64
    inafter
    -0.62
    iesis
    -0.62
     Buhari
    -0.61
    ysuckle
    -0.61
     tâche
    -0.60
     ciascuno
    -0.60
    POSITIVE LOGITS
     extreme
    2.79
     Extreme
    2.68
    Extreme
    2.66
    extreme
    2.59
     extrême
    2.03
     extremes
    2.02
     extre
    1.85
     extremo
    1.76
     ekst
    1.70
     Extrem
    1.69
    Activations Density 0.064%

    No Known Activations