© 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. 9-GEMMASCOPE-RES-16K
    11. 5842
    Prev
    Next
    INDEX
    Explanations

    definitions and grammatical structures related to language and syntax

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.62
    adeloupe
    -0.53
     ExecuteAsync
    -0.49
    EDEFAULT
    -0.47
     rospy
    -0.47
    kenny
    -0.45
    enares
    -0.45
    eynman
    -0.45
    MLLoader
    -0.45
    wyn
    -0.45
    POSITIVE LOGITS
    ViewFeatures
    0.35
     ArrayAdapter
    0.34
    brainly
    0.33
     Meksiku
    0.33
    новништво
    0.33
    ValueStyle
    0.33
    StoryboardSegue
    0.31
    UniformLocation
    0.31
     émission
    0.30
    Atsauces
    0.29
    Activations Density 0.465%

    No Known Activations