© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 3485
    Prev
    Next
    INDEX
    Explanations

    speculative and conjectural statements about potential outcomes or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presumably
    -0.89
     apparently
    -0.88
    presumably
    -0.87
     evidently
    -0.84
    apparently
    -0.79
     probably
    -0.79
     Presumably
    -0.77
     undoubtedly
    -0.77
    おそらく
    -0.76
     clearly
    -0.75
    POSITIVE LOGITS
     someday
    0.75
     subconsciously
    0.66
     algún
    0.65
     subconscious
    0.62
     alguno
    0.59
     overkill
    0.55
     unconsciously
    0.54
     sogar
    0.54
     qualche
    0.53
     inadvertently
    0.53
    Activations Density 0.556%

    No Known Activations