© 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. 12672
    Prev
    Next
    INDEX
    Explanations

    concepts related to social significance and cultural analysis

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

    Academic or political discourse

    np_acts-logits-general · gemini-2.0-flash

    academic discourse and concepts

    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
    +#+
    -0.77
    iſen
    -0.69
     محفوظة
    -0.67
     propOrder
    -0.65
    ésultats
    -0.65
     $_"
    -0.64
     pleaſure
    -0.64
    ConstraintMaker
    -0.64
    edicated
    -0.62
    ſchen
    -0.60
    POSITIVE LOGITS
     Gegenstand
    0.35
     uitgenodigd
    0.33
     political
    0.32
     partial
    0.32
    探讨
    0.31
    （
    0.31
     provocative
    0.31
    立场
    0.31
     gegenwär
    0.31
     cited
    0.31
    Activations Density 0.771%

    No Known Activations