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. 1-GEMMASCOPE-RES-16K
    6. 13399
    Prev
    Next
    INDEX
    Explanations

    references to locations and names associated with Shanghai

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '},
    
    -0.65
    เผ
    -0.55
    '):
    
    -0.54
     ná
    -0.53
    "):
    
    -0.53
     Савезне
    -0.53
    >--}}
    -0.53
    saraba
    -0.52
    ()]);
    -0.52
    rí
    -0.52
    POSITIVE LOGITS
     و
    1.93
    و
    1.14
     ו
    1.10
     وو
    0.87
     وَ
    0.75
    ว
    0.72
     ও
    0.71
     lisäksi
    0.70
     بلکه
    0.70
     umana
    0.69
    Activations Density 0.033%

    No Known Activations