© 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. 14054
    Prev
    Next
    INDEX
    Explanations

    instances of whitespace or gaps in the text structure

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

    Code snippets and file paths

    np_acts-logits-general · gemini-2.0-flash

    function definitions

    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
     julk
    -0.50
     enää
    -0.45
     jembatan
    -0.45
    Tamaño
    -0.45
     myös
    -0.44
     jopa
    -0.44
    AddTagHelper
    -0.44
     vielä
    -0.44
    Dimensões
    -0.43
     literaria
    -0.43
    POSITIVE LOGITS
     Мексичка
    0.60
    GEBURTSDATUM
    0.58
     مرئيه
    0.54
    })$}
    0.54
    ########.
    0.50
     astore
    0.50
    djangoproject
    0.49
     sire
    0.47
    ]),
    0.47
    SaveVideo
    0.47
    Activations Density 0.063%

    No Known Activations