© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8018
    Prev
    Next
    INDEX
    Explanations

    the various forms of the verb "come" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.48
    ריים
    -0.35
    coleg
    -0.35
     Ran
    -0.35
    UrlResolution
    -0.34
     bershka
    -0.34
     Run
    -0.34
    HomeAsUp
    -0.34
    Blan
    -0.33
    holic
    -0.33
    POSITIVE LOGITS
    ագրություններ
    0.70
    ImageContext
    0.66
     المعيارى
    0.64
     Winaray
    0.58
     crashing
    0.56
    AndEndTag
    0.56
    httphttps
    0.54
     '\\;'
    0.53
     handy
    0.52
     InputDecoration
    0.51
    Activations Density 0.138%

    No Known Activations