© 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. 15-GEMMASCOPE-RES-16K
    11. 5379
    Prev
    Next
    INDEX
    Explanations

    references to education and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.66
    KURZBESCHREIBUNG
    -0.59
     مشين
    -0.56
    GOTREF
    -0.56
    stateProvider
    -0.54
    ActionCreators
    -0.50
    IsContent
    -0.49
    WriteTagHelper
    -0.48
     onCancelled
    -0.47
     viewDidLoad
    -0.47
    POSITIVE LOGITS
     exercises
    0.78
     Exercises
    0.67
    exercises
    0.64
    Exercises
    0.62
     exercise
    0.62
     Exercise
    0.60
     EXERCISES
    0.58
     prompts
    0.56
    Exercise
    0.56
     questionnaires
    0.55
    Activations Density 0.490%

    No Known Activations