© 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. 10515
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect personal experiences and reflections

    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
    IntoConstraints
    -0.74
     Chwiliwch
    -0.74
    FieldBuilder
    -0.72
     kasarigan
    -0.67
    WriteBarrier
    -0.59
     onCancelled
    -0.59
    writeFieldEnd
    -0.58
    EDEFAULT
    -0.57
     defaultstate
    -0.54
    tagHelperRunner
    -0.53
    POSITIVE LOGITS
    こういう
    0.75
    こういった
    0.58
     corporations
    0.58
     humans
    0.56
     zoos
    0.55
     prisons
    0.55
     cults
    0.54
     democracies
    0.54
     animals
    0.53
     computers
    0.52
    Activations Density 0.856%

    No Known Activations