© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 114881
    Prev
    Next
    INDEX
    Explanations

    variables and their related operations in programming

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

    return values from functions

    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
     يتيمه
    -0.77
     nahilalakip
    -0.74
     disambiguazione
    -0.73
    ThroughAttribute
    -0.72
    saraba
    -0.70
     kaarangay
    -0.68
    NUMX
    -0.67
     Normdatei
    -0.64
    __(/*!
    -0.64
     հղումներ
    -0.63
    POSITIVE LOGITS
     nonetheless
    0.39
     nevertheless
    0.38
    XmlRootElement
    0.38
    est
    0.37
     already
    0.36
    return
    0.35
    .
    0.35
     return
    0.35
    base
    0.32
    ModelAndView
    0.32
    Activations Density 0.017%

    No Known Activations