© 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. 31226
    Prev
    Next
    INDEX
    Explanations

    references to competitions and related events or merchandise

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

    research meeting, radio commentary, Small Groups

    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
     simply
    -0.23
     secuen
    -0.23
     even
    -0.22
     dokonce
    -0.22
     oorsp
    -0.22
     myndig
    -0.22
     highly
    -0.22
     aarde
    -0.22
     esfuer
    -0.21
     Behör
    -0.21
    POSITIVE LOGITS
    GEBURTS
    0.96
     resourceCulture
    0.89
     ब्रेकडाउन
    0.78
     Италијани
    0.78
    Personensuche
    0.77
    ValueStyle
    0.74
    enumii
    0.73
    ſelben
    0.71
     nahilalakip
    0.71
    Rhestr
    0.70
    Activations Density 0.008%

    No Known Activations