© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6302
    Prev
    Next
    INDEX
    Explanations

    concepts related to stability and stability assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.69
    ↵
    -0.66
      
    -0.66
     cu
    -0.64
     pod
    -0.63
    I
    -0.63
    墨
    -0.62
    <eos>
    -0.62
     Pod
    -0.61
    ond
    -0.60
    POSITIVE LOGITS
     Stable
    1.74
     stabilisation
    1.64
     Reſ
    1.57
     Stabili
    1.57
     myſelf
    1.57
     stabilization
    1.57
    Stable
    1.56
     itſelf
    1.56
    unstable
    1.56
     stabilize
    1.55
    Activations Density 0.191%

    No Known Activations