© 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. 36-GEMMASCOPE-RES-16K
    11. 6212
    Prev
    Next
    INDEX
    Explanations

    numerical data and quantities related to historical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.68
    RegressionTest
    -0.58
    脚注の使い方
    -0.57
     utafitiHapana
    -0.57
     JpaRepository
    -0.56
     autorytatywna
    -0.53
    ineſs
    -0.51
    principalColumn
    -0.51
     pleaſure
    -0.50
    AutoField
    -0.49
    POSITIVE LOGITS
     thousands
    1.43
    Thousands
    1.19
     thousand
    1.18
    thousands
    1.18
     Thousands
    1.16
     milliers
    0.96
     THOUS
    0.95
    thousand
    0.91
    三千
    0.86
     thous
    0.85
    Activations Density 1.194%

    No Known Activations