© 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. 33-GEMMASCOPE-RES-16K
    11. 11331
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to individual experiences or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.57
     <<<<<<<<<<<<<<
    -0.56
    WebElementEntity
    -0.51
    PullParser
    -0.51
    HeaderText
    -0.50
    TabIndex
    -0.49
     continúas
    -0.48
     становника
    -0.46
    Facial
    -0.46
    InputTagHelper
    -0.45
    POSITIVE LOGITS
     mind
    0.65
     lungs
    0.58
     eyes
    0.56
     kidneys
    0.54
     legs
    0.52
     hips
    0.50
     feet
    0.49
     ears
    0.48
     senses
    0.48
     soul
    0.47
    Activations Density 0.327%

    No Known Activations