© 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. 9767
    Prev
    Next
    INDEX
    Explanations

    references to glass as a material or object

    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
    Portale
    -0.87
    epam
    -0.79
    anzug
    -0.78
     relève
    -0.75
    Monique
    -0.74
     Soit
    -0.73
    maksud
    -0.73
     répon
    -0.73
     veik
    -0.73
     démar
    -0.73
    POSITIVE LOGITS
     Glass
    1.51
     GLASS
    1.50
     glass
    1.43
    Glass
    1.42
    glass
    1.41
    GLASS
    1.38
     glas
    1.21
     Glas
    1.21
     glasses
    1.18
    Glas
    1.17
    Activations Density 0.079%

    No Known Activations