© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1132
    Prev
    Next
    INDEX
    Explanations

    references to personal reflections or intentions in writing

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    uncertainty or possibility

    np_acts-logits-general · gemini-2.0-flash

    quantifying or qualifying something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     absolutely
    -0.99
     totally
    -0.87
     completely
    -0.87
     absolutamente
    -0.83
     utterly
    -0.82
    absolutely
    -0.81
     unbelievably
    -0.80
    絶対に
    -0.79
     абсолютно
    -0.79
     incredibly
    -0.78
    POSITIVE LOGITS
     somewhat
    1.10
    somewhat
    1.02
     Somewhat
    0.94
    Somewhat
    0.90
     algunos
    0.82
     biraz
    0.82
     perhaps
    0.81
     algunas
    0.80
     некото
    0.80
     cierta
    0.79
    Activations Density 3.877%

    No Known Activations