© 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. 7-GEMMASCOPE-RES-16K
    11. 11960
    Prev
    Next
    INDEX
    Explanations

    concepts of relationships and the impact of social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipot
    -0.69
    lamabad
    -0.61
     insurers
    -0.61
     virtually
    -0.60
     unmatched
    -0.60
     endless
    -0.59
     unrivalled
    -0.56
    Bliss
    -0.56
     boundless
    -0.56
     limitless
    -0.55
    POSITIVE LOGITS
     מאוד
    0.86
    Very
    0.77
     alot
    0.75
     very
    0.75
     Very
    0.74
     sekali
    0.73
    PerformLayout
    0.73
     جدًا
    0.71
    sehr
    0.69
    very
    0.68
    Activations Density 0.435%

    No Known Activations