© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14755
    Prev
    Next
    INDEX
    Explanations

    references to glass and its various forms or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    первых
    -0.57
    रीदारी
    -0.48
    extérieur
    -0.48
    ثة
    -0.48
    щото
    -0.46
     gracia
    -0.46
    ellent
    -0.44
    Sortie
    -0.44
     biens
    -0.44
     trò
    -0.44
    POSITIVE LOGITS
     panes
    0.77
    reportWebVitals
    0.74
     useStyles
    0.70
    Glas
    0.70
    fibre
    0.70
     Glas
    0.70
     Glass
    0.69
    morphism
    0.69
     GLASS
    0.68
     Bottles
    0.67
    Activations Density 0.096%

    No Known Activations