© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14788
    Prev
    Next
    INDEX
    Explanations

    references to user interface elements and their functionality

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

    Code, series, file, screen, or prompt appearing

    np_acts-logits-general · gemini-2.0-flash

    displaying lists and screens

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Pol
    -0.40
     ESPEC
    -0.40
     Vivi
    -0.40
    
    -0.40
     espe
    -0.40
     recruited
    -0.37
     работал
    -0.37
     particularly
    -0.37
     Ati
    -0.36
     cand
    -0.36
    POSITIVE LOGITS
    yntaxException
    0.63
    bootstrapcdn
    0.57
    PointerException
    0.57
    GOTREF
    0.54
    ParallelGroup
    0.48
    mobileqq
    0.48
    CppMethod
    0.48
    原始内容存档于
    0.46
     يتيمه
    0.45
    ValueStyle
    0.45
    Activations Density 0.439%

    No Known Activations