© 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. 8-GEMMASCOPE-RES-16K
    11. 11072
    Prev
    Next
    INDEX
    Explanations

    strong emotional descriptors and affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.73
    somewhat
    -0.68
    较为
    -0.68
     somewhat
    -0.66
     algunos
    -0.65
     agak
    -0.63
    較
    -0.62
     durchaus
    -0.62
    较
    -0.61
     некото
    -0.61
    POSITIVE LOGITS
     amazing
    0.93
     gorgeous
    0.92
    amazing
    0.88
     brilliant
    0.87
     incredible
    0.84
     unbelievably
    0.84
     marvelous
    0.83
     utterly
    0.82
    incredible
    0.80
    brilliant
    0.79
    Activations Density 0.835%

    No Known Activations