© 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. 15071
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "it" and its variations in context

    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
    tagHelperRunner
    -0.71
    帖最后由
    -0.63
     EconPapers
    -0.58
    principalTable
    -0.56
    UrlResolution
    -0.54
    astéroïdes
    -0.53
    новништво
    -0.53
    ValueStyle
    -0.51
     betweenstory
    -0.51
     informée
    -0.50
    POSITIVE LOGITS
     seems
    2.33
     seem
    2.28
     Seems
    1.99
    seems
    1.98
     seemed
    1.92
    Seems
    1.91
    seem
    1.78
     parece
    1.68
     semblent
    1.62
     semble
    1.61
    Activations Density 0.520%

    No Known Activations