© 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. 37-GEMMASCOPE-RES-16K
    11. 5242
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sequence of actions or procedures intended to achieve specific outcomes

    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
    исленность
    -0.55
    SequentialGroup
    -0.50
    ftagPool
    -0.48
     fubject
    -0.48
    Jeografia
    -0.46
     становника
    -0.46
     raiſ
    -0.45
    adaptiveStyles
    -0.45
    jména
    -0.44
    Населення
    -0.43
    POSITIVE LOGITS
     avoid
    1.09
     ensure
    0.87
    avoid
    0.82
     properly
    0.82
     prevent
    0.79
     Avoid
    0.77
     избежать
    0.73
     insure
    0.71
     avoiding
    0.71
     maximize
    0.69
    Activations Density 0.623%

    No Known Activations