© 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. 15-GEMMASCOPE-RES-16K
    11. 4823
    Prev
    Next
    INDEX
    Explanations

    expressions indicating high quality or positive evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skyscanner
    -0.65
     Assisi
    -0.63
    prnewswire
    -0.61
    pédie
    -0.61
    ليب
    -0.57
     Schaefer
    -0.57
    venirs
    -0.57
     Archbishop
    -0.57
    Programming
    -0.56
     ejus
    -0.56
    POSITIVE LOGITS
     well
    1.06
     Well
    1.04
    Well
    0.98
     WELL
    0.95
    well
    0.88
     wells
    0.84
    Wells
    0.79
     Welles
    0.78
     Wells
    0.76
     wel
    0.71
    Activations Density 0.107%

    No Known Activations