© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4779
    Prev
    Next
    INDEX
    Explanations

    discussions about persons and their interactions or characteristics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    tagHelperRunner
    -0.58
     initComponents
    -0.50
    forRoot
    -0.40
    URBANA
    -0.40
    /***/
    -0.39
    下载附件
    -0.38
    MenuInflater
    -0.37
     onCreateView
    -0.36
    LabelTagHelper
    -0.36
    ItemBackground
    -0.35
    POSITIVE LOGITS
     person
    3.03
     persons
    2.69
     Person
    2.38
    person
    2.38
    Person
    2.25
     people
    2.23
     personnes
    2.23
     personen
    2.16
    persons
    2.16
     PERSON
    2.16
    Activations Density 0.679%

    No Known Activations