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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 12939
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to software licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.58
     itſelf
    -0.51
     Wikiseite
    -0.51
     *__
    -0.50
     *)__
    -0.50
    \#\#
    -0.48
    enumi
    -0.48
    MLLoader
    -0.48
    ikusbot
    -0.48
     محفوظة
    -0.47
    POSITIVE LOGITS
    //
    0.43
    Хьажоргаш
    0.38
    #
    0.35
     Administrativna
    0.34
     galite
    0.34
     énergé
    0.34
     bahawa
    0.33
     coreana
    0.33
     termica
    0.32
    లాలు
    0.32
    Activations Density 0.425%

    No Known Activations