© 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. 1623
    Prev
    Next
    INDEX
    Explanations

    references to rarity and limited editions of items

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

    "limited" and "rarity"

    np_acts-logits-general · gemini-2.0-flash

    limited and rare quantities

    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
     CURIAM
    -0.49
    Personendaten
    -0.44
     snippetHide
    -0.41
    acuation
    -0.40
    struzioni
    -0.40
    点此举报
    -0.39
     grecque
    -0.39
    partement
    -0.37
    ItemBackground
    -0.37
     chaussure
    -0.36
    POSITIVE LOGITS
     rarer
    0.73
     rare
    0.71
     rarest
    0.70
    Rare
    0.63
     rarity
    0.62
     Rare
    0.62
     limited
    0.56
     RARE
    0.54
     rares
    0.53
    rarity
    0.53
    Activations Density 0.194%

    No Known Activations