© 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. 38-GEMMASCOPE-RES-16K
    11. 7686
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to technical problems or glitches, particularly in computing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     praticamente
    -0.47
     تقری
    -0.42
    几乎
    -0.40
     prácticamente
    -0.40
     практически
    -0.40
     pratiquement
    -0.39
     practically
    -0.39
    幾乎
    -0.36
     rischi
    -0.36
     seem
    -0.36
    POSITIVE LOGITS
     somehow
    0.85
     faulty
    0.83
     algum
    0.80
     때문
    0.77
     algún
    0.77
     something
    0.76
     valami
    0.74
     defective
    0.73
     alguma
    0.72
     malfunction
    0.71
    Activations Density 0.823%

    No Known Activations