© 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. 11297
    Prev
    Next
    INDEX
    Explanations

    programming constructs and language-specific syntax

    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
    ScopeManager
    -0.80
    featureID
    -0.70
    verwijspagina
    -0.68
    
    -0.66
    脚注の使い方
    -0.66
     surla
    -0.65
    principalTable
    -0.63
    ロウィン
    -0.62
     Audiodateien
    -0.61
     "..\..\
    -0.60
    POSITIVE LOGITS
    ↵↵
    0.53
    ↵
    0.39
    ↵↵↵
    0.35
     adoption
    0.35
     
    0.35
     BE
    0.34
     performance
    0.32
     kept
    0.32
    发表于
    0.32
     اعتبار
    0.32
    Activations Density 0.395%

    No Known Activations