© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12303
    Prev
    Next
    INDEX
    Explanations

    the term "high" in various contexts, often related to quality or performance attributes

    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
     Trotter
    -0.73
     Creatures
    -0.73
    adaptiveStyles
    -0.72
     redé
    -0.69
     entière
    -0.68
    UserAgent
    -0.67
    creatures
    -0.67
     voyez
    -0.67
     Schäfer
    -0.67
    MENAFN
    -0.67
    POSITIVE LOGITS
     High
    1.84
    High
    1.80
     high
    1.79
    high
    1.70
     HIGH
    1.69
    HIGH
    1.64
     Low
    1.38
    Low
    1.35
    高
    1.33
     low
    1.27
    Activations Density 0.148%

    No Known Activations