© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    phrases that involve the act of raising or elevating various concepts, issues, or entities

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

    "raise" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    raise children, money, questions

    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
    AppData
    -0.46
    ServletContext
    -0.46
    tanleria
    -0.46
    ритори
    -0.46
     SCC
    -0.45
    Gemeinden
    -0.45
     Venn
    -0.43
     Cont
    -0.43
    olog
    -0.42
    cartItems
    -0.42
    POSITIVE LOGITS
    Raise
    1.01
     raise
    0.97
     Raise
    0.96
    raise
    0.92
     raising
    0.86
     Raising
    0.84
    raised
    0.82
    Raising
    0.81
    rise
    0.80
     raises
    0.80
    Activations Density 0.225%

    No Known Activations