© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7283
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts, particularly those related to functions, error handling, and data structures in a code context

    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
     gärna
    -0.34
    <h2>
    -0.33
    <eos>
    -0.32
     sociala
    -0.32
    fører
    -0.30
        
    -0.30
     vux
    -0.29
    ibm
    -0.28
     те
    -0.28
     république
    -0.28
    POSITIVE LOGITS
    AndEndTag
    0.91
     disambiguazione
    0.88
    IUrlHelper
    0.84
    featureID
    0.83
    tvguidetime
    0.78
     utafitiHapana
    0.74
     ویکی‌آمباردا
    0.70
    RTEE
    0.68
    exitRule
    0.68
    TypedDataSet
    0.68
    Activations Density 0.530%

    No Known Activations