© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10444
    Prev
    Next
    INDEX
    Explanations

    discussions related to issues and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after negative sentiment words

    np_acts-logits-general · gemini-2.0-flash

    issues, shit, incident

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typically
    -0.25
    
    -0.24
     samma
    -0.23
     same
    -0.22
    <unused60>
    -0.21
     regular
    -0.20
     výkon
    -0.20
     a
    -0.19
    </h3>
    -0.19
    <unused61>
    -0.19
    POSITIVE LOGITS
    transQ
    0.97
     Administrativna
    0.95
    RegressionTest
    0.93
     betweenstory
    0.92
    TypedDataSet
    0.91
    XmlAccessorType
    0.89
     ivelany
    0.87
    writeFieldEnd
    0.85
    <unused16>
    0.84
    <unused41>
    0.84
    Activations Density 0.927%

    No Known Activations