© 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. 11-GEMMASCOPE-RES-16K
    11. 6462
    Prev
    Next
    INDEX
    Explanations

    phrases indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skosten
    -0.75
    geology
    -0.69
    newArrayList
    -0.68
    Koz
    -0.68
     Koz
    -0.65
    URLException
    -0.64
    topus
    -0.63
     ComVisible
    -0.63
     transmettre
    -0.62
     Kos
    -0.61
    POSITIVE LOGITS
    Better
    1.41
     BETTER
    1.40
     Better
    1.37
    better
    1.37
     better
    1.30
     beter
    0.98
     bedre
    0.97
     besseren
    0.97
     besser
    0.90
     betterment
    0.90
    Activations Density 0.055%

    No Known Activations