© 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. 106334
    Prev
    Next
    INDEX
    Explanations

    structured data formats and programming syntax

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

    numbers and prime factors

    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
     Cuatro
    -0.42
     CURIAM
    -0.41
     lievito
    -0.41
    badlogic
    -0.39
     progressive
    -0.38
     all
    -0.38
     Numerade
    -0.38
     henvisninger
    -0.38
     increment
    -0.37
     unknownFields
    -0.37
    POSITIVE LOGITS
     begge
    1.00
     nakalista
    0.85
    这两个
    0.82
     båda
    0.81
     ambos
    0.77
     beiden
    0.74
     beide
    0.73
     keduanya
    0.72
     two
    0.71
     beider
    0.71
    Activations Density 0.277%

    No Known Activations