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. 6-GEMMASCOPE-RES-16K
    6. 3337
    Prev
    Next
    INDEX
    Explanations

    references to subsets or substructures within mathematical contexts

    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
     tfsi
    -0.96
    ing
    -0.89
    rsiniz
    -0.88
    بوابة
    -0.79
    azgo
    -0.79
     APS
    -0.78
     serpents
    -0.76
    ی
    -0.76
     TPE
    -0.76
     TSI
    -0.75
    POSITIVE LOGITS
    							
    1.00
     Ruck
    0.97
    						
    0.88
    ifun
    0.86
    withIdentifier
    0.85
     Calla
    0.84
     Kitts
    0.84
    								
    0.81
    EndProject
    0.79
    ])));
    0.78
    Activations Density 0.094%

    No Known Activations