© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4951
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to causal inference and statistical estimation methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.57
     household
    -0.57
    涕
    -0.47
     top
    -0.46
     personal
    -0.45
     civilian
    -0.44
    gir
    -0.44
    ISTO
    -0.43
    AndGet
    -0.43
    crip
    -0.43
    POSITIVE LOGITS
    TintMode
    1.10
    addCriterion
    0.92
    EDEFAULT
    0.90
    :✨
    0.88
    Personensuche
    0.87
    WithIOException
    0.86
     فريبيس
    0.86
    ThroughAttribute
    0.85
    Bioaccumulative
    0.85
     jsPsych
    0.84
    Activations Density 3.066%

    No Known Activations