© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10883
    Prev
    Next
    INDEX
    Explanations

    references to physical dependence and withdrawal symptoms related to opioids

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

    Negative sentiment/loss

    np_acts-logits-general · gemini-2.0-flash

    minimize withdrawal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.58
    CodeAttribute
    -0.50
    rophore
    -0.49
    Източници
    -0.48
    rangle
    -0.47
     maïs
    -0.46
    هرست
    -0.45
    QApplication
    -0.44
     pranzo
    -0.44
     esconder
    -0.44
    POSITIVE LOGITS
     loss
    0.89
    Losing
    0.82
    loss
    0.77
    IntoConstraints
    0.77
     Loss
    0.77
    Loss
    0.74
     Losing
    0.73
     Verlust
    0.73
     replacement
    0.72
     upset
    0.70
    Activations Density 0.505%

    No Known Activations