© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70884
    Prev
    Next
    INDEX
    Explanations

    elements related to coding logic and conditional checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    parentheses in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.92
     CreateTagHelper
    -0.73
    RegistryLite
    -0.69
    __":
    
    -0.69
    __':
    
    -0.66
    interopRequire
    -0.64
    TargetException
    -0.63
    ollectionView
    -0.63
    __':
    -0.62
    fromnode
    -0.62
    POSITIVE LOGITS
     somewhere
    0.33
    somewhere
    0.31
    during
    0.28
    τους
    0.26
     during
    0.25
    ︎
    0.25
     anum
    0.24
     fabricants
    0.24
     SALUD
    0.24
     beho
    0.24
    Activations Density 0.016%

    No Known Activations