© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 12210
    Prev
    Next
    INDEX
    Explanations

    opinions and thoughts expressed about a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apparently
    -0.90
     Apparently
    -0.82
     aparentemente
    -0.81
    apparently
    -0.79
     seemingly
    -0.78
     reportedly
    -0.75
    Apparently
    -0.75
     supposedly
    -0.71
     supuestamente
    -0.71
     schein
    -0.70
    POSITIVE LOGITS
     fairest
    0.57
     pretty
    0.56
     fair
    0.54
     ganska
    0.52
     fairly
    0.52
     overall
    0.51
     unfairly
    0.48
    pretty
    0.47
     fairer
    0.46
     underrated
    0.46
    Activations Density 0.281%

    No Known Activations