Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10751
    Prev
    Next
    INDEX
    Explanations

    references to earning or financial gain

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

    "Earn" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    earning money or other gains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subpackage
    -0.40
    <h1>
    -0.40
     attacked
    -0.39
     attacks
    -0.38
     regions
    -0.38
     attack
    -0.37
     section
    -0.37
     fire
    -0.37
     Parrish
    -0.37
    cityId
    -0.36
    POSITIVE LOGITS
     earn
    1.91
     earned
    1.90
    earned
    1.88
    Earn
    1.84
     earns
    1.73
     earning
    1.72
     Earned
    1.69
    earn
    1.67
    earning
    1.65
     Earn
    1.61
    Activations Density 0.121%

    No Known Activations