© 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. 6-GEMMASCOPE-RES-16K
    11. 13685
    Prev
    Next
    INDEX
    Explanations

    patterns related to email communication and e-commerce

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.83
    expandindo
    -0.79
    ]")]
    -0.78
    ̍t
    -0.76
    verwijspagina
    -0.70
    SBATCH
    -0.70
     يتيمه
    -0.68
    UserScript
    -0.68
    VolleyError
    -0.66
     sạn
    -0.66
    POSITIVE LOGITS
     electronic
    1.09
     online
    1.06
     Electronic
    1.03
    online
    1.00
     digital
    0.99
     elektron
    0.93
    electronic
    0.93
    Electronic
    0.93
     virtual
    0.90
     Online
    0.90
    Activations Density 0.131%

    No Known Activations