© 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. 5-GEMMASCOPE-RES-16K
    11. 6511
    Prev
    Next
    INDEX
    Explanations

    references to software and its characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adpleegd
    -0.81
    ]-->
    -0.76
     ActionResult
    -0.75
     Tare
    -0.75
     Dignity
    -0.74
     Kicks
    -0.74
     Replay
    -0.73
    AsUp
    -0.72
     Dij
    -0.72
     Balt
    -0.72
    POSITIVE LOGITS
     software
    2.23
     Software
    2.05
    software
    1.90
    Software
    1.85
     SOFTWARE
    1.69
    SOFTWARE
    1.62
    oftware
    1.60
    软件
    1.58
     softwares
    1.57
     logiciel
    1.48
    Activations Density 0.063%

    No Known Activations