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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5005
    Prev
    Next
    INDEX
    Explanations

    terms related to financial losses and profitability issues

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

    Profitability, losses, and operating results

    np_acts-logits-general · gemini-2.0-flash

    profit and loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gewe
    -0.68
    EndInit
    -0.59
     createState
    -0.57
    bouncycastle
    -0.53
     onCreateView
    -0.49
    INCREF
    -0.49
     Sj
    -0.47
    Nazionale
    -0.47
     Kase
    -0.47
     TextInputType
    -0.46
    POSITIVE LOGITS
     profit
    0.89
     profitability
    0.89
    profit
    0.82
     operating
    0.81
     Profit
    0.78
     profits
    0.77
     unprofitable
    0.75
     EBITDA
    0.74
     margins
    0.74
     profitable
    0.72
    Activations Density 0.221%

    No Known Activations