© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 2850
    Prev
    Next
    INDEX
    Explanations

    expressions indicating certainty and potential outcomes

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     locul
    -0.47
     receiving
    -0.43
    hon
    -0.42
    المناصب
    -0.42
     hon
    -0.41
     meyd
    -0.39
     můžete
    -0.38
    哎
    -0.38
     fisuras
    -0.37
    직
    -0.37
    POSITIVE LOGITS
    certainly
    0.88
     ExecuteAsync
    0.80
     certainly
    0.79
     Certainly
    0.74
     propOrder
    0.73
    MockBean
    0.72
     שוליים
    0.71
    Certainly
    0.70
     виправивши
    0.69
    ISupport
    0.66
    Activations Density 0.161%

    No Known Activations