© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 6925
    Prev
    Next
    INDEX
    Explanations

    monetary terms and associated symbols, indicating a focus on financial transactions and gambling concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Â
    -1.17
    Ã
    -1.08
     Â
    -0.98
     = 
    -0.91
    â
    -0.90
     Ã
    -0.89
     ${\
    -0.88
     â
    -0.85
     –,
    -0.79
    <em>
    -0.79
    POSITIVE LOGITS
     🙏
    1.62
     🥰
    1.60
     🤣
    1.54
     🔥
    1.53
    ️⃣
    1.53
     👇
    1.51
     ❤️
    1.50
     🙌
    1.50
     🤩
    1.48
     😂
    1.48
    Activations Density 0.415%

    No Known Activations