© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 1964
    Prev
    Next
    INDEX
    Explanations

    references to conflict and its resolution or aftermath

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     there
    -0.46
     יש
    -0.46
     υπάρχ
    -0.45
    個人的には
    -0.45
    Есть
    -0.44
     есть
    -0.43
     Есть
    -0.42
    そうそう
    -0.42
     بالنسبة
    -0.41
     existem
    -0.40
    POSITIVE LOGITS
     realizing
    1.24
     realising
    1.14
     fearing
    1.12
     knowing
    1.06
     believing
    1.05
     aware
    1.02
     sensing
    1.00
     unable
    1.00
    Unable
    0.99
    Knowing
    0.98
    Activations Density 0.577%

    No Known Activations