© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7158
    Prev
    Next
    INDEX
    Explanations

    financial terms related to the U.S. dollar and economic policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     relâche
    -0.52
    ✨:
    -0.48
    AndEndTag
    -0.44
    rscheinlich
    -0.42
    ább
    -0.40
    ApiOperation
    -0.40
     Nội
    -0.40
    estris
    -0.40
    SequentialGroup
    -0.40
     Deliber
    -0.40
    POSITIVE LOGITS
     currency
    0.83
     currencies
    0.78
     Currency
    0.66
    Currency
    0.62
    currency
    0.61
    currencies
    0.54
     transfieras
    0.54
     Normdatei
    0.52
     moneda
    0.52
    kháu
    0.52
    Activations Density 0.117%

    No Known Activations