© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4153
    Prev
    Next
    INDEX
    Explanations

    references to prices in various contexts

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

    "price" and price changes

    np_acts-logits-general · gemini-2.0-flash

    price targets and dynamics

    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
     twin
    -0.46
     Hoo
    -0.46
     Hofmann
    -0.46
     Holm
    -0.46
     minor
    -0.45
     seven
    -0.45
     unanimous
    -0.43
     dallo
    -0.43
    Rüyada
    -0.43
     ten
    -0.42
    POSITIVE LOGITS
    Price
    1.10
     price
    1.05
    PRICE
    1.02
     Price
    1.02
    price
    1.02
     getPrice
    1.00
     PRICE
    0.97
    getPrice
    0.92
     Prices
    0.89
     prices
    0.88
    Activations Density 0.082%

    No Known Activations