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. 2-GEMMASCOPE-RES-16K
    6. 14964
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to measures and kernel functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.90
     Diſ
    -0.89
     Houſe
    -0.80
     Anſ
    -0.78
     faſt
    -0.76
     Beſ
    -0.75
     houſe
    -0.74
    PRNewswire
    -0.74
     Bandar
    -0.73
    DMETHOD
    -0.71
    POSITIVE LOGITS
    imageshack
    0.65
     reindeer
    0.64
    onomía
    0.60
    genossen
    0.59
    Παραπομπές
    0.57
    Lydia
    0.57
     Lydia
    0.56
     resourceCulture
    0.55
    ")));
    
    0.55
     personalmente
    0.55
    Activations Density 0.843%

    No Known Activations