© 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. 7940
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantities and statistical measurements

    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
     meste
    -0.70
     '*')
    -0.64
     saken
    -0.63
     récompenses
    -0.61
     تانيه
    -0.60
     الحره
    -0.60
     campeones
    -0.57
     dachte
    -0.57
     degradability
    -0.57
    Trails
    -0.56
    POSITIVE LOGITS
     numberOf
    1.13
     number
    1.11
    numberOf
    1.05
     fewer
    1.00
    NumberOf
    0.93
    DockStyle
    0.92
     Number
    0.91
    numbered
    0.90
    WithMany
    0.88
    antMatchers
    0.88
    Activations Density 0.235%

    No Known Activations