© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 8450
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "dis-" and its associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neceſſ
    -0.55
     ſtill
    -0.55
     diſt
    -0.55
     ſtate
    -0.55
     myſelf
    -0.54
    RefNanny
    -0.53
    AxisAlignment
    -0.52
     digitais
    -0.49
     themſelves
    -0.48
     Anſ
    -0.47
    POSITIVE LOGITS
     Dis
    0.64
     DIS
    0.52
    Dis
    0.51
    dis
    0.47
    DIS
    0.42
     dis
    0.42
    enance
    0.41
    mtrl
    0.38
    туга
    0.38
    webElementXpaths
    0.35
    Activations Density 0.241%

    No Known Activations