© 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-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 9147
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of potential issues or concerns in a user context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELTS
    -0.63
     AssemblyTitle
    -0.61
     useAppContext
    -0.60
     iprot
    -0.54
    ">//
    -0.54
    omock
    -0.51
    -0.51
    extField
    -0.51
    autique
    -0.50
    QMetaType
    -0.50
    POSITIVE LOGITS
     risk
    2.16
    risk
    1.89
     Risk
    1.84
     risks
    1.77
    Risk
    1.72
     RISK
    1.66
     risked
    1.58
     danger
    1.55
     riesgo
    1.50
    risks
    1.45
    Activations Density 0.375%

    No Known Activations