© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1130
    Prev
    Next
    INDEX
    Explanations

    terms related to coding and programming concepts

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

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    technical and programming terms

    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
    kjø
    -0.57
     maș
    -0.57
     mijne
    -0.56
     lisäksi
    -0.54
     argint
    -0.53
    ohjel
    -0.52
    záll
    -0.51
    ïque
    -0.50
     väli
    -0.50
    ltä
    -0.50
    POSITIVE LOGITS
    styleType
    0.85
    دانشنامهٔ
    0.74
    transQ
    0.73
     <>",
    0.71
    uxxxx
    0.69
    ThroughAttribute
    0.69
    UrlResolution
    0.64
    complexContent
    0.63
    CloseOperation
    0.63
     صوتيه
    0.63
    Activations Density 0.069%

    No Known Activations