© 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. 6-GEMMASCOPE-RES-16K
    11. 12084
    Prev
    Next
    INDEX
    Explanations

    expressions indicating something is intriguing, notable, or thought-provoking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ClientRect
    -0.82
     étoient
    -0.81
     ſever
    -0.80
     poffible
    -0.75
     Jefus
    -0.74
     ſtre
    -0.73
     juſ
    -0.72
     ſta
    -0.72
     juſt
    -0.72
     ormai
    -0.71
    POSITIVE LOGITS
     interesting
    1.83
    interesting
    1.77
     Interesting
    1.64
    Interesting
    1.60
     fascinating
    1.41
     interesante
    1.38
     interessante
    1.37
     intéressante
    1.32
     interessant
    1.30
     interessantes
    1.24
    Activations Density 0.086%

    No Known Activations