© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8448
    Prev
    Next
    INDEX
    Explanations

    references to high school and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.55
     defaultstate
    -0.44
    AnchorTagHelper
    -0.44
    UnusedPrivate
    -0.43
    ValueStyle
    -0.42
    assertArray
    -0.39
    AddTagHelper
    -0.38
     ends
    -0.38
    principalColumn
    -0.38
     continúas
    -0.37
    POSITIVE LOGITS
     college
    0.79
    college
    0.71
     prison
    0.68
     highschool
    0.68
     undergrad
    0.65
     undergraduate
    0.60
     lycée
    0.59
    College
    0.59
     university
    0.57
     COLLEGE
    0.56
    Activations Density 0.187%

    No Known Activations